TOP ACTIVATIONS
MAX = 0.115

wanted to go sailing on one of the y ach ts
the cheese and add the topp ings . Lily and Ben
could balance really high on one foot and shake the ground
Max wanted to get a closer look at the sail .
and even balance himself on one foot . One day ,
dad gave him a gentle fishing rod and told him to
they can add their own topp ings too . Sara chooses
and wanted to ride on one . His mom my said
fish . He had a fishing rod and a bucket ready
started to chew on some seaw eed . Mary was so
how he could lean on one leg . He lifted his
the pond and got his fishing rod . He cast the
Lily ! I admire your fishing skills . You caught a
and decided to take a closer look . He decided to
, dinner time !" exclaimed Nem o . But
, and we can catch one . Do you want to
He wanted to get a closer look , so he walked
Bob o a big hug and put him back in the
He wanted to get a closer look , so he walked
old lady with a mis chie vous tw inkle in her

MIN ACTIVATIONS
MIN = -0.105

room . She sees the twins slapping each other and the
hall . She sees the twins fighting over the box .
they did . She says they will not have any jam
room . She sees the twins fighting and the beads on
play outside . Mom says they can play with their blocks
broken lamp and the crying twins . She is angry and
sees the puzzle and the twins . She is not happy
broken lamp and the crying twins . She is angry and
sees the car and the twins . She is not happy
! He asked grown - ups to help him wipe them
and selfish . She says they have to share their toys
the music . She says they can listen to both songs
not happy . She says they have to stop fighting and
not happy . She says they have to clean up and
But she sees Sara and Ben 's faces . They are
their lesson . She says they have to stay in their
not happy . She says they have to hurry . She
forgive them . She says they have to learn their lesson
and kind . She says they have to wait until they
and angry . She says they are naughty and silly .

INTERVAL 0.060 - 0.115
CONTAINS 0.229%

They wanted to eat something y ummy . Mom said she
, forty - five , forty - six , forty -
had a bird 's eye view of the whole world .
Tim my smiled and nodded his head . He
. Jack had a guitar that he loved to play .

INTERVAL 0.005 - 0.060
CONTAINS 41.286%

. They pet his nose and his man e and his
. The little girl couldn 't believe what she
Grand ma hugged them and said , � � € �
said , " Yes , but it hurts . I should
it was a treasure !" The man picks up

INTERVAL -0.050 - 0.005
CONTAINS 57.568%

little girl was very scared . She had never climbed a
, but she wanted to go with her mom . She
ran away and hid behind a tree . She cried and
They saw a boy running towards them . The boy was
He heard his mom and dad talking to someone . He

INTERVAL -0.105 - -0.050
CONTAINS 0.916%

They do not see Fl uffy watching them from the shore
moment . She felt sorry for Max too . She said
was always more . L ily started to feel
. Tim saw Lily with his aer opl ane
shines again . They take turns holding the button
Token wanted
Token ID2227
Feature activation+3.23e-02

Pos logit contributions
 flavor+0.006
 tal+0.006
imm+0.006
boat+0.006
bye+0.006
Neg logit contributions
otion-0.006
 wasting-0.006
 fighting-0.006
 grounded-0.005
 sewing-0.005
Token to
Token ID284
Feature activation+4.51e-02

Pos logit contributions
imm+0.068
boat+0.064
oc+0.062
 tal+0.062
ww+0.060
Neg logit contributions
 wasting-0.050
 fighting-0.048
 sewing-0.046
otion-0.045
 grounded-0.041
Token go
Token ID467
Feature activation+2.01e-02

Pos logit contributions
imm+0.099
 tal+0.095
ww+0.092
boat+0.091
iest+0.088
Neg logit contributions
 fighting-0.059
 wasting-0.059
otion-0.059
 sewing-0.053
 typing-0.048
Token sailing
Token ID28499
Feature activation+4.71e-02

Pos logit contributions
imm+0.039
 tal+0.039
 flavor+0.038
boat+0.038
bye+0.037
Neg logit contributions
otion-0.029
 wasting-0.028
 fighting-0.028
 sewing-0.026
 grounded-0.026
Token on
Token ID319
Feature activation+1.08e-02

Pos logit contributions
ww+0.111
 tal+0.109
imm+0.108
 flavour+0.102
 flavor+0.101
Neg logit contributions
 fighting-0.043
 wasting-0.041
otion-0.040
 downstairs-0.038
 sewing-0.038
Token one
Token ID530
Feature activation+1.15e-01

Pos logit contributions
imm+0.021
boat+0.020
 flavor+0.020
bye+0.020
 tal+0.019
Neg logit contributions
otion-0.017
 wasting-0.016
 fighting-0.015
 sewing-0.015
 grounded-0.014
Token of
Token ID286
Feature activation+5.70e-03

Pos logit contributions
imm+0.231
 tal+0.230
ages+0.219
haw+0.215
cream+0.213
Neg logit contributions
 end-0.121
 downstairs-0.104
 backstage-0.103
 sewing-0.102
 salon-0.102
Token the
Token ID262
Feature activation+2.59e-02

Pos logit contributions
imm+0.010
 flavor+0.010
 tal+0.010
boat+0.010
bye+0.010
Neg logit contributions
otion-0.009
 wasting-0.009
 fighting-0.008
 grounded-0.008
 sewing-0.008
Token y
Token ID331
Feature activation+8.52e-02

Pos logit contributions
imm+0.044
 tal+0.041
 flavor+0.038
bye+0.037
boat+0.037
Neg logit contributions
 wasting-0.047
 fighting-0.046
otion-0.045
 grounded-0.043
 sewing-0.041
Tokenach
Token ID620
Feature activation+4.11e-02

Pos logit contributions
boat+0.169
 tal+0.165
imm+0.154
iest+0.152
ah+0.152
Neg logit contributions
 fighting-0.096
otion-0.095
oken-0.090
 wasting-0.089
els-0.084
Tokents
Token ID912
Feature activation+2.75e-02

Pos logit contributions
 tal+0.066
boat+0.062
imm+0.061
bye+0.061
ww+0.060
Neg logit contributions
otion-0.074
 fighting-0.071
 wasting-0.070
 sewing-0.065
 grounded-0.062
Token the
Token ID262
Feature activation+2.49e-02

Pos logit contributions
imm+0.035
boat+0.034
bye+0.034
 tal+0.034
 flavor+0.033
Neg logit contributions
otion-0.033
 wasting-0.031
 fighting-0.030
 grounded-0.028
 sewing-0.027
Token cheese
Token ID9891
Feature activation+3.81e-02

Pos logit contributions
imm+0.036
boat+0.036
bye+0.035
 tal+0.034
 flavor+0.033
Neg logit contributions
 wasting-0.048
otion-0.046
 fighting-0.046
 grounded-0.043
 sewing-0.043
Token and
Token ID290
Feature activation+3.18e-02

Pos logit contributions
bye+0.073
 tal+0.071
imm+0.071
 flavor+0.070
boat+0.069
Neg logit contributions
otion-0.057
 wasting-0.055
 fighting-0.054
 sewing-0.049
 grounded-0.047
Token add
Token ID751
Feature activation+3.43e-02

Pos logit contributions
imm+0.055
boat+0.055
bye+0.053
iest+0.051
 tal+0.049
Neg logit contributions
 wasting-0.059
 fighting-0.055
otion-0.052
 sewing-0.051
 grounded-0.049
Token the
Token ID262
Feature activation+1.76e-02

Pos logit contributions
boat+0.067
imm+0.067
bye+0.066
 tal+0.064
ww+0.061
Neg logit contributions
 wasting-0.050
otion-0.049
 fighting-0.048
 sewing-0.043
 grounded-0.042
Token topp
Token ID23126
Feature activation+1.09e-01

Pos logit contributions
imm+0.025
boat+0.025
 tal+0.024
bye+0.024
 flavor+0.023
Neg logit contributions
 wasting-0.034
otion-0.034
 fighting-0.034
 grounded-0.031
 sewing-0.031
Tokenings
Token ID654
Feature activation-3.35e-03

Pos logit contributions
bye+0.205
 tal+0.203
boat+0.190
 lifetime+0.186
 memorable+0.186
Neg logit contributions
otion-0.145
 fighting-0.138
els-0.131
 spills-0.123
 wasting-0.122
Token.
Token ID13
Feature activation-1.66e-02

Pos logit contributions
otion+0.007
 wasting+0.006
 fighting+0.006
 grounded+0.006
 sewing+0.006
Neg logit contributions
 flavor-0.005
boat-0.005
imm-0.005
 tal-0.005
bye-0.005
Token Lily
Token ID20037
Feature activation+4.41e-03

Pos logit contributions
otion+0.030
 wasting+0.028
 grounded+0.027
 fighting+0.026
osing+0.025
Neg logit contributions
 flavor-0.027
 tal-0.025
imm-0.025
 flavour-0.025
boat-0.025
Token and
Token ID290
Feature activation+1.70e-05

Pos logit contributions
 flavor+0.008
boat+0.008
 tal+0.008
imm+0.008
bye+0.008
Neg logit contributions
otion-0.007
 wasting-0.007
 fighting-0.007
 grounded-0.006
 sewing-0.006
Token Ben
Token ID3932
Feature activation-4.93e-03

Pos logit contributions
 flavor+0.000
boat+0.000
imm+0.000
 tal+0.000
bye+0.000
Neg logit contributions
otion-0.000
 wasting-0.000
 fighting-0.000
 grounded-0.000
 sewing-0.000
Token could
Token ID714
Feature activation+1.53e-02

Pos logit contributions
 tal+0.033
imm+0.032
boat+0.032
 flavor+0.032
iest+0.031
Neg logit contributions
otion-0.024
 wasting-0.024
 fighting-0.023
 grounded-0.022
 sewing-0.022
Token balance
Token ID5236
Feature activation+8.79e-03

Pos logit contributions
 tal+0.026
imm+0.026
 flavor+0.026
boat+0.025
ww+0.025
Neg logit contributions
otion-0.026
 wasting-0.026
 fighting-0.024
 grounded-0.023
 sewing-0.023
Token really
Token ID1107
Feature activation+3.35e-02

Pos logit contributions
 flavor+0.015
imm+0.015
boat+0.015
bye+0.015
 tal+0.014
Neg logit contributions
otion-0.015
 wasting-0.014
 fighting-0.014
 grounded-0.013
 sewing-0.013
Token high
Token ID1029
Feature activation+1.58e-02

Pos logit contributions
imm+0.068
 flavor+0.067
 tal+0.067
boat+0.066
bye+0.064
Neg logit contributions
otion-0.046
 wasting-0.044
 fighting-0.041
 grounded-0.040
osing-0.037
Token on
Token ID319
Feature activation+2.83e-02

Pos logit contributions
 flavor+0.030
 tal+0.030
boat+0.030
imm+0.029
bye+0.029
Neg logit contributions
otion-0.023
 wasting-0.023
 fighting-0.022
 grounded-0.020
 sewing-0.019
Token one
Token ID530
Feature activation+1.07e-01

Pos logit contributions
imm+0.049
boat+0.047
bye+0.047
ww+0.044
 flavor+0.044
Neg logit contributions
otion-0.049
 wasting-0.049
 fighting-0.046
 sewing-0.043
 grounded-0.042
Token foot
Token ID2366
Feature activation+4.92e-02

Pos logit contributions
imm+0.213
 tal+0.203
ww+0.203
Ar+0.202
emo+0.202
Neg logit contributions
otion-0.104
 sewing-0.103
 salon-0.098
 end-0.098
 piano-0.092
Token and
Token ID290
Feature activation+2.45e-02

Pos logit contributions
 tal+0.095
imm+0.094
 flavor+0.092
ww+0.091
bye+0.089
Neg logit contributions
otion-0.073
 fighting-0.067
 wasting-0.064
 sewing-0.062
 grounded-0.060
Token shake
Token ID13279
Feature activation+3.28e-02

Pos logit contributions
imm+0.043
 tal+0.040
 flavor+0.040
iest+0.039
boat+0.039
Neg logit contributions
otion-0.041
 wasting-0.041
 fighting-0.040
 grounded-0.038
 sewing-0.037
Token the
Token ID262
Feature activation+1.68e-02

Pos logit contributions
imm+0.057
boat+0.055
bye+0.054
ww+0.053
 flavor+0.053
Neg logit contributions
 fighting-0.054
otion-0.054
 wasting-0.054
 grounded-0.047
 sewing-0.046
Token ground
Token ID2323
Feature activation+2.25e-02

Pos logit contributions
imm+0.026
 flavor+0.024
boat+0.024
 tal+0.024
bye+0.024
Neg logit contributions
 wasting-0.032
otion-0.032
 fighting-0.030
 grounded-0.029
 sewing-0.029
Token Max
Token ID5436
Feature activation+3.42e-02

Pos logit contributions
imm+0.044
boat+0.044
 tal+0.043
iest+0.043
 flavor+0.042
Neg logit contributions
otion-0.028
 wasting-0.026
 fighting-0.026
 grounded-0.023
 sewing-0.023
Token wanted
Token ID2227
Feature activation+2.93e-02

Pos logit contributions
iest+0.072
imm+0.071
 tal+0.071
boat+0.068
umm+0.067
Neg logit contributions
 fighting-0.045
 wasting-0.043
otion-0.039
 grounded-0.038
 sewing-0.037
Token to
Token ID284
Feature activation+6.00e-02

Pos logit contributions
imm+0.065
boat+0.058
 tal+0.058
oc+0.057
ww+0.057
Neg logit contributions
 fighting-0.044
 wasting-0.043
 sewing-0.041
otion-0.038
 crying-0.036
Token get
Token ID651
Feature activation+1.88e-02

Pos logit contributions
imm+0.134
ww+0.132
umm+0.129
 tal+0.126
iest+0.117
Neg logit contributions
 fighting-0.071
 sewing-0.064
 wasting-0.063
otion-0.061
 grounded-0.060
Token a
Token ID257
Feature activation+7.74e-02

Pos logit contributions
imm+0.037
 tal+0.036
 flavor+0.034
boat+0.034
ww+0.034
Neg logit contributions
 wasting-0.028
 fighting-0.028
otion-0.027
 grounded-0.026
 sewing-0.025
Token closer
Token ID5699
Feature activation+1.06e-01

Pos logit contributions
imm+0.146
 tal+0.125
umm+0.116
oc+0.116
iest+0.115
Neg logit contributions
 fighting-0.131
 sewing-0.128
 wasting-0.118
 crying-0.116
 grounded-0.115
Token look
Token ID804
Feature activation+2.88e-02

Pos logit contributions
imm+0.283
umm+0.274
 flavours+0.267
oc+0.261
cream+0.261
Neg logit contributions
 fighting-0.046
 crying-0.041
otion-0.038
 or-0.028
 wardrobe-0.028
Token at
Token ID379
Feature activation+1.51e-02

Pos logit contributions
 tal+0.055
imm+0.053
boat+0.052
 flavor+0.052
bye+0.049
Neg logit contributions
otion-0.046
 wasting-0.043
 fighting-0.043
 grounded-0.039
osing-0.038
Token the
Token ID262
Feature activation+1.24e-02

Pos logit contributions
imm+0.031
boat+0.030
ww+0.030
bye+0.030
 flavor+0.030
Neg logit contributions
otion-0.021
 wasting-0.021
 fighting-0.020
 grounded-0.018
 sewing-0.018
Token sail
Token ID14936
Feature activation+3.59e-02

Pos logit contributions
imm+0.014
 tal+0.013
 flavor+0.013
boat+0.012
bye+0.011
Neg logit contributions
otion-0.029
 wasting-0.028
 fighting-0.028
 grounded-0.027
 sewing-0.026
Token.
Token ID13
Feature activation+4.55e-02

Pos logit contributions
 tal+0.066
imm+0.064
ww+0.064
 flavor+0.062
 flavour+0.059
Neg logit contributions
otion-0.060
 fighting-0.056
 wasting-0.053
 sewing-0.049
 grounded-0.049
Token and
Token ID290
Feature activation+2.43e-02

Pos logit contributions
imm+0.048
 tal+0.048
 flavor+0.047
ww+0.047
boat+0.046
Neg logit contributions
otion-0.039
 fighting-0.038
 wasting-0.038
 sewing-0.036
 grounded-0.034
Token even
Token ID772
Feature activation+4.44e-02

Pos logit contributions
imm+0.041
 tal+0.039
ww+0.039
 flavor+0.038
iest+0.038
Neg logit contributions
otion-0.041
 wasting-0.041
 fighting-0.040
 grounded-0.038
 sewing-0.038
Token balance
Token ID5236
Feature activation+9.08e-03

Pos logit contributions
imm+0.078
 tal+0.077
bye+0.076
ww+0.075
 flavor+0.071
Neg logit contributions
 wasting-0.073
 fighting-0.069
 sewing-0.068
otion-0.066
 grounded-0.066
Token himself
Token ID2241
Feature activation+2.51e-02

Pos logit contributions
 flavor+0.014
boat+0.014
imm+0.014
bye+0.014
 tal+0.014
Neg logit contributions
otion-0.017
 wasting-0.016
 fighting-0.015
 grounded-0.015
 sewing-0.015
Token on
Token ID319
Feature activation+2.39e-02

Pos logit contributions
 tal+0.050
 flavor+0.050
bye+0.049
boat+0.049
imm+0.049
Neg logit contributions
otion-0.034
 wasting-0.033
 fighting-0.032
 grounded-0.029
 sewing-0.029
Token one
Token ID530
Feature activation+1.03e-01

Pos logit contributions
imm+0.040
boat+0.039
bye+0.039
 tal+0.037
ww+0.037
Neg logit contributions
 wasting-0.041
otion-0.041
 fighting-0.040
 sewing-0.038
 grounded-0.036
Token foot
Token ID2366
Feature activation+4.47e-02

Pos logit contributions
imm+0.202
ww+0.200
oy+0.199
 tal+0.195
Ar+0.190
Neg logit contributions
 sewing-0.108
 salon-0.102
otion-0.097
She-0.093
 end-0.093
Token.
Token ID13
Feature activation+2.73e-02

Pos logit contributions
 tal+0.082
imm+0.080
ww+0.078
 flavor+0.077
bye+0.075
Neg logit contributions
otion-0.070
 fighting-0.064
 wasting-0.062
 sewing-0.062
 grounded-0.059
Token One
Token ID1881
Feature activation+6.16e-02

Pos logit contributions
 tal+0.051
iest+0.051
boat+0.051
ww+0.051
imm+0.050
Neg logit contributions
otion-0.043
 fighting-0.040
 wasting-0.038
 sewing-0.036
Acc-0.035
Token day
Token ID1110
Feature activation+3.23e-02

Pos logit contributions
imm+0.122
 tal+0.120
eed+0.118
wood+0.109
oy+0.106
Neg logit contributions
 fighting-0.073
 wasting-0.072
 living-0.071
 crying-0.071
 grounded-0.070
Token,
Token ID11
Feature activation+2.39e-02

Pos logit contributions
imm+0.061
boat+0.060
 tal+0.060
bye+0.056
 flavor+0.055
Neg logit contributions
otion-0.053
 fighting-0.051
 wasting-0.048
osing-0.042
 grounded-0.042
Token dad
Token ID9955
Feature activation+1.65e-02

Pos logit contributions
imm+0.160
iest+0.146
boat+0.144
 tal+0.144
ww+0.140
Neg logit contributions
 fighting-0.045
 wasting-0.038
 twins-0.036
 arguing-0.029
 grounded-0.029
Token gave
Token ID2921
Feature activation+3.55e-03

Pos logit contributions
 tal+0.028
imm+0.028
 flavor+0.027
boat+0.026
bye+0.026
Neg logit contributions
otion-0.028
 wasting-0.027
 fighting-0.027
 grounded-0.026
 sewing-0.024
Token him
Token ID683
Feature activation+4.18e-02

Pos logit contributions
 flavor+0.006
imm+0.006
 tal+0.006
boat+0.006
bye+0.006
Neg logit contributions
otion-0.006
 wasting-0.005
 fighting-0.005
 grounded-0.005
 sewing-0.005
Token a
Token ID257
Feature activation+8.23e-02

Pos logit contributions
imm+0.085
boat+0.083
 tal+0.079
iest+0.079
bye+0.078
Neg logit contributions
 wasting-0.057
 fighting-0.052
otion-0.051
 grounded-0.050
 sewing-0.048
Token gentle
Token ID10296
Feature activation+8.34e-02

Pos logit contributions
imm+0.160
bye+0.133
umm+0.131
 tal+0.127
iest+0.124
Neg logit contributions
 wasting-0.128
 fighting-0.126
 sewing-0.120
 grounded-0.113
otion-0.107
Token fishing
Token ID12478
Feature activation+1.02e-01

Pos logit contributions
imm+0.130
umm+0.100
cream+0.097
 tal+0.090
ww+0.089
Neg logit contributions
 fighting-0.145
otion-0.141
 wasting-0.137
 sewing-0.133
 grounded-0.130
Token rod
Token ID15299
Feature activation+5.90e-02

Pos logit contributions
imm+0.149
iest+0.120
 tal+0.119
ww+0.116
 avail+0.111
Neg logit contributions
 fighting-0.185
 sewing-0.175
 grounded-0.169
 wasting-0.169
 living-0.159
Token and
Token ID290
Feature activation+5.51e-02

Pos logit contributions
imm+0.116
ww+0.110
 tal+0.110
 flavor+0.107
bye+0.103
Neg logit contributions
otion-0.082
 fighting-0.080
 wasting-0.079
 sewing-0.075
 grounded-0.071
Token told
Token ID1297
Feature activation+4.82e-03

Pos logit contributions
imm+0.110
iest+0.095
 tal+0.095
boat+0.093
bye+0.091
Neg logit contributions
 wasting-0.095
 fighting-0.093
 grounded-0.082
 sewing-0.078
otion-0.077
Token him
Token ID683
Feature activation+2.53e-02

Pos logit contributions
boat+0.008
imm+0.008
 flavor+0.008
 tal+0.008
bye+0.008
Neg logit contributions
otion-0.008
 wasting-0.008
 fighting-0.007
 grounded-0.007
 sewing-0.007
Token to
Token ID284
Feature activation+4.49e-02

Pos logit contributions
imm+0.041
boat+0.039
 tal+0.039
 flavor+0.037
bye+0.037
Neg logit contributions
otion-0.047
 wasting-0.045
 fighting-0.043
 grounded-0.040
 sewing-0.040
Token they
Token ID484
Feature activation-4.22e-02

Pos logit contributions
otion+0.026
 wasting+0.025
 grounded+0.024
 fighting+0.024
 sewing+0.023
Neg logit contributions
 flavor-0.015
 tal-0.014
iest-0.014
boat-0.013
bye-0.013
Token can
Token ID460
Feature activation+2.25e-02

Pos logit contributions
otion+0.078
 wasting+0.068
 fighting+0.063
 sewing+0.063
Acc+0.063
Neg logit contributions
 flavor-0.073
 flavour-0.067
boat-0.064
iest-0.061
bye-0.061
Token add
Token ID751
Feature activation+4.17e-02

Pos logit contributions
 tal+0.042
imm+0.040
boat+0.040
ww+0.039
bye+0.039
Neg logit contributions
otion-0.037
 wasting-0.036
 fighting-0.035
 sewing-0.032
 grounded-0.031
Token their
Token ID511
Feature activation+2.02e-02

Pos logit contributions
boat+0.086
imm+0.086
bye+0.084
 tal+0.079
ww+0.076
Neg logit contributions
 wasting-0.059
 fighting-0.057
otion-0.053
 sewing-0.050
 grounded-0.047
Token own
Token ID898
Feature activation+2.60e-02

Pos logit contributions
boat+0.031
imm+0.031
bye+0.029
 tal+0.028
iest+0.028
Neg logit contributions
 wasting-0.038
 fighting-0.037
otion-0.037
 sewing-0.035
 grounded-0.034
Token topp
Token ID23126
Feature activation+1.01e-01

Pos logit contributions
imm+0.042
boat+0.042
bye+0.041
 tal+0.040
ww+0.039
Neg logit contributions
 wasting-0.046
otion-0.045
 fighting-0.045
 sewing-0.043
 grounded-0.041
Tokenings
Token ID654
Feature activation+2.57e-02

Pos logit contributions
 tal+0.185
bye+0.184
boat+0.178
ww+0.176
 lifetime+0.170
Neg logit contributions
otion-0.123
els-0.123
 fighting-0.120
 twins-0.108
ains-0.105
Token too
Token ID1165
Feature activation+3.24e-02

Pos logit contributions
 tal+0.047
imm+0.046
boat+0.045
 flavor+0.044
bye+0.043
Neg logit contributions
otion-0.042
 wasting-0.040
 fighting-0.038
 grounded-0.036
 sewing-0.035
Token.
Token ID13
Feature activation-8.06e-04

Pos logit contributions
imm+0.055
boat+0.055
 tal+0.054
bye+0.051
 flavor+0.051
Neg logit contributions
otion-0.056
 wasting-0.056
 fighting-0.054
 sewing-0.049
 grounded-0.048
Token Sara
Token ID24799
Feature activation-2.72e-03

Pos logit contributions
otion+0.002
 wasting+0.001
 fighting+0.001
 grounded+0.001
 sewing+0.001
Neg logit contributions
 flavor-0.001
boat-0.001
imm-0.001
 tal-0.001
bye-0.001
Token chooses
Token ID19769
Feature activation+4.28e-02

Pos logit contributions
otion+0.004
 wasting+0.004
 fighting+0.003
 grounded+0.003
 sewing+0.003
Neg logit contributions
 flavor-0.005
boat-0.005
imm-0.005
 tal-0.005
bye-0.005
Token and
Token ID290
Feature activation+1.66e-02

Pos logit contributions
 tal+0.027
imm+0.026
 flavor+0.026
boat+0.025
ww+0.025
Neg logit contributions
otion-0.024
 wasting-0.023
 fighting-0.023
 sewing-0.021
 grounded-0.021
Token wanted
Token ID2227
Feature activation+1.63e-02

Pos logit contributions
imm+0.029
 tal+0.029
boat+0.028
 flavor+0.027
bye+0.027
Neg logit contributions
otion-0.027
 wasting-0.027
 fighting-0.026
 sewing-0.024
 grounded-0.024
Token to
Token ID284
Feature activation+3.81e-02

Pos logit contributions
imm+0.026
 tal+0.025
boat+0.025
bye+0.024
 flavor+0.024
Neg logit contributions
otion-0.030
 wasting-0.029
 fighting-0.029
 sewing-0.028
 grounded-0.027
Token ride
Token ID6594
Feature activation+2.46e-02

Pos logit contributions
imm+0.079
 tal+0.077
iest+0.074
ww+0.074
boat+0.073
Neg logit contributions
 fighting-0.053
 wasting-0.051
 sewing-0.050
otion-0.050
 typing-0.045
Token on
Token ID319
Feature activation+3.44e-05

Pos logit contributions
imm+0.046
 tal+0.046
 flavor+0.044
ww+0.044
bye+0.044
Neg logit contributions
otion-0.037
 fighting-0.036
 wasting-0.035
 sewing-0.033
 grounded-0.032
Token one
Token ID530
Feature activation+1.00e-01

Pos logit contributions
 flavor+0.000
boat+0.000
imm+0.000
 tal+0.000
bye+0.000
Neg logit contributions
otion-0.000
 wasting-0.000
 fighting-0.000
 grounded-0.000
 sewing-0.000
Token.
Token ID13
Feature activation+3.52e-02

Pos logit contributions
 tal+0.202
 mun+0.193
imm+0.188
 flavours+0.179
 flavour+0.178
Neg logit contributions
 sewing-0.117
otion-0.115
 fighting-0.113
 salon-0.113
 piano-0.108
Token His
Token ID2399
Feature activation+1.33e-02

Pos logit contributions
iest+0.064
ww+0.064
 tal+0.063
imm+0.060
boat+0.060
Neg logit contributions
otion-0.055
 fighting-0.055
 sewing-0.051
 wasting-0.051
Acc-0.047
Token mom
Token ID1995
Feature activation+1.11e-03

Pos logit contributions
 tal+0.024
imm+0.024
boat+0.024
 flavor+0.023
iest+0.023
Neg logit contributions
otion-0.021
 fighting-0.021
 wasting-0.020
 sewing-0.019
 grounded-0.019
Tokenmy
Token ID1820
Feature activation+8.50e-03

Pos logit contributions
 flavor+0.002
 tal+0.002
boat+0.002
imm+0.002
bye+0.002
Neg logit contributions
otion-0.002
 wasting-0.001
 fighting-0.001
 grounded-0.001
 sewing-0.001
Token said
Token ID531
Feature activation+1.64e-03

Pos logit contributions
 tal+0.013
 flavor+0.013
imm+0.013
boat+0.013
bye+0.012
Neg logit contributions
otion-0.016
 wasting-0.015
 fighting-0.015
 grounded-0.015
 sewing-0.014
Token fish
Token ID5916
Feature activation+3.49e-02

Pos logit contributions
imm+0.174
 tal+0.134
iest+0.127
umm+0.125
bye+0.121
Neg logit contributions
 fighting-0.149
 wasting-0.140
otion-0.119
 sees-0.118
 arguing-0.118
Token.
Token ID13
Feature activation+3.74e-02

Pos logit contributions
imm+0.065
 tal+0.063
 flavor+0.061
ww+0.059
iest+0.058
Neg logit contributions
 fighting-0.056
otion-0.056
 wasting-0.055
 grounded-0.050
 sewing-0.048
Token He
Token ID679
Feature activation+3.79e-02

Pos logit contributions
iest+0.070
ww+0.066
 tal+0.066
imm+0.065
boat+0.064
Neg logit contributions
otion-0.062
 fighting-0.062
 wasting-0.059
 sewing-0.053
 Why-0.051
Token had
Token ID550
Feature activation+3.94e-02

Pos logit contributions
iest+0.078
imm+0.077
 tal+0.075
boat+0.073
umm+0.072
Neg logit contributions
 fighting-0.051
 wasting-0.051
 grounded-0.046
otion-0.043
 sewing-0.040
Token a
Token ID257
Feature activation+6.46e-02

Pos logit contributions
imm+0.093
iest+0.089
boat+0.088
umm+0.085
bye+0.085
Neg logit contributions
 wasting-0.049
 fighting-0.046
 grounded-0.039
 sewing-0.035
otion-0.035
Token fishing
Token ID12478
Feature activation+1.00e-01

Pos logit contributions
imm+0.135
iest+0.124
bye+0.117
boat+0.115
cream+0.113
Neg logit contributions
 fighting-0.100
 wasting-0.091
 sewing-0.083
 arguing-0.083
 crying-0.080
Token rod
Token ID15299
Feature activation+3.90e-02

Pos logit contributions
imm+0.138
 tal+0.125
iest+0.121
 avail+0.120
filled+0.116
Neg logit contributions
 fighting-0.179
 grounded-0.162
 wasting-0.158
 sewing-0.155
 living-0.152
Token and
Token ID290
Feature activation+2.73e-02

Pos logit contributions
imm+0.079
 tal+0.079
 flavor+0.075
bye+0.074
boat+0.073
Neg logit contributions
otion-0.054
 wasting-0.052
 fighting-0.052
 sewing-0.047
 grounded-0.045
Token a
Token ID257
Feature activation+4.57e-02

Pos logit contributions
imm+0.045
 tal+0.041
boat+0.041
iest+0.039
bye+0.039
Neg logit contributions
 wasting-0.052
 fighting-0.051
otion-0.050
 grounded-0.046
 sewing-0.046
Token bucket
Token ID19236
Feature activation+4.60e-02

Pos logit contributions
imm+0.078
bye+0.065
iest+0.065
boat+0.063
 tal+0.061
Neg logit contributions
 fighting-0.087
 wasting-0.085
 sewing-0.081
otion-0.077
 crying-0.076
Token ready
Token ID3492
Feature activation+4.52e-02

Pos logit contributions
 tal+0.083
ww+0.080
imm+0.079
 flavor+0.078
bye+0.077
Neg logit contributions
otion-0.073
 wasting-0.070
 fighting-0.070
 sewing-0.063
 grounded-0.060
Token started
Token ID2067
Feature activation+1.25e-02

Pos logit contributions
imm+0.110
 tal+0.103
bye+0.102
iest+0.101
boat+0.100
Neg logit contributions
 wasting-0.091
 fighting-0.087
otion-0.081
 grounded-0.078
 hey-0.069
Token to
Token ID284
Feature activation+2.29e-02

Pos logit contributions
boat+0.019
imm+0.019
 flavor+0.019
bye+0.019
 tal+0.019
Neg logit contributions
otion-0.024
 wasting-0.024
 fighting-0.023
 sewing-0.022
 grounded-0.021
Token chew
Token ID34722
Feature activation+7.06e-03

Pos logit contributions
imm+0.032
iest+0.032
ww+0.032
boat+0.031
bye+0.031
Neg logit contributions
 wasting-0.046
otion-0.045
 fighting-0.044
 sewing-0.040
 grounded-0.040
Token on
Token ID319
Feature activation+1.32e-02

Pos logit contributions
imm+0.011
boat+0.011
 flavor+0.011
 tal+0.011
bye+0.011
Neg logit contributions
otion-0.013
 wasting-0.012
 fighting-0.011
 grounded-0.011
 sewing-0.011
Token some
Token ID617
Feature activation+5.20e-02

Pos logit contributions
boat+0.023
imm+0.023
bye+0.023
 flavor+0.022
 tal+0.022
Neg logit contributions
otion-0.022
 wasting-0.021
 fighting-0.020
 sewing-0.019
 grounded-0.019
Token seaw
Token ID32085
Feature activation+9.99e-02

Pos logit contributions
imm+0.088
boat+0.086
bye+0.085
 tal+0.077
ww+0.076
Neg logit contributions
 wasting-0.093
 fighting-0.089
otion-0.082
 sewing-0.079
oken-0.074
Tokeneed
Token ID2308
Feature activation+3.12e-02

Pos logit contributions
boat+0.139
bye+0.135
iest+0.124
 Andy+0.124
 flavor+0.120
Neg logit contributions
arl-0.152
otion-0.149
osing-0.148
oken-0.146
 sewing-0.145
Token.
Token ID13
Feature activation+2.52e-02

Pos logit contributions
imm+0.052
 tal+0.052
bye+0.051
 flavor+0.051
ww+0.050
Neg logit contributions
otion-0.054
 wasting-0.051
 fighting-0.051
 sewing-0.046
 grounded-0.045
Token Mary
Token ID5335
Feature activation+2.33e-02

Pos logit contributions
boat+0.047
imm+0.045
iest+0.043
 flavor+0.043
 tal+0.042
Neg logit contributions
otion-0.044
 wasting-0.040
 fighting-0.038
 grounded-0.035
osing-0.035
Token was
Token ID373
Feature activation+1.30e-02

Pos logit contributions
imm+0.038
boat+0.038
iest+0.037
 flavor+0.037
bye+0.037
Neg logit contributions
 wasting-0.040
otion-0.039
 fighting-0.038
 grounded-0.037
 sewing-0.035
Token so
Token ID523
Feature activation+2.67e-02

Pos logit contributions
boat+0.023
imm+0.022
 flavor+0.022
bye+0.022
 tal+0.022
Neg logit contributions
otion-0.022
 wasting-0.022
 fighting-0.021
 grounded-0.020
 sewing-0.019
Token how
Token ID703
Feature activation+2.31e-02

Pos logit contributions
otion+0.024
 wasting+0.023
 grounded+0.022
 fighting+0.022
 sewing+0.021
Neg logit contributions
 flavor-0.019
boat-0.019
 tal-0.018
imm-0.018
iest-0.018
Token he
Token ID339
Feature activation+3.18e-02

Pos logit contributions
imm+0.037
 tal+0.036
 flavor+0.034
boat+0.034
iest+0.032
Neg logit contributions
 wasting-0.043
otion-0.042
 fighting-0.042
 grounded-0.039
 sewing-0.038
Token could
Token ID714
Feature activation+3.08e-02

Pos logit contributions
 tal+0.058
imm+0.056
ww+0.055
 flavor+0.055
boat+0.055
Neg logit contributions
otion-0.047
 wasting-0.047
 fighting-0.045
 grounded-0.044
 sewing-0.042
Token lean
Token ID10904
Feature activation+6.34e-03

Pos logit contributions
imm+0.056
 tal+0.056
ww+0.056
boat+0.053
 flavor+0.052
Neg logit contributions
otion-0.050
 wasting-0.047
 fighting-0.046
 sewing-0.042
 grounded-0.042
Token on
Token ID319
Feature activation+7.04e-03

Pos logit contributions
 flavor+0.011
 tal+0.010
imm+0.010
boat+0.010
bye+0.010
Neg logit contributions
otion-0.011
 wasting-0.011
 fighting-0.010
 grounded-0.010
 sewing-0.009
Token one
Token ID530
Feature activation+9.98e-02

Pos logit contributions
imm+0.011
 flavor+0.011
boat+0.011
 tal+0.011
bye+0.011
Neg logit contributions
otion-0.013
 wasting-0.012
 fighting-0.012
 grounded-0.011
 sewing-0.011
Token leg
Token ID1232
Feature activation+3.17e-02

Pos logit contributions
imm+0.191
 tal+0.187
ww+0.186
oy+0.184
 hamb+0.181
Neg logit contributions
otion-0.113
 sewing-0.108
 salon-0.106
 piano-0.104
She-0.103
Token.
Token ID13
Feature activation+2.28e-02

Pos logit contributions
imm+0.051
 flavor+0.051
 tal+0.051
ww+0.049
boat+0.048
Neg logit contributions
otion-0.056
 wasting-0.052
 fighting-0.052
 sewing-0.049
 grounded-0.049
Token He
Token ID679
Feature activation+1.97e-02

Pos logit contributions
iest+0.031
imm+0.030
 flavor+0.030
boat+0.029
 tal+0.029
Neg logit contributions
otion-0.047
 fighting-0.046
 wasting-0.045
 grounded-0.042
 sewing-0.042
Token lifted
Token ID13663
Feature activation+1.85e-02

Pos logit contributions
imm+0.033
boat+0.033
 flavor+0.032
 tal+0.032
iest+0.032
Neg logit contributions
otion-0.032
 wasting-0.032
 fighting-0.031
 grounded-0.030
 sewing-0.029
Token his
Token ID465
Feature activation+3.56e-02

Pos logit contributions
imm+0.029
 flavor+0.029
boat+0.028
ww+0.028
 tal+0.028
Neg logit contributions
otion-0.034
 fighting-0.032
 wasting-0.032
 grounded-0.030
 sewing-0.029
Token the
Token ID262
Feature activation+3.46e-02

Pos logit contributions
imm+0.038
iest+0.036
boat+0.035
ww+0.035
bye+0.035
Neg logit contributions
 wasting-0.023
otion-0.022
 fighting-0.022
 sewing-0.020
 grounded-0.020
Token pond
Token ID16723
Feature activation+3.04e-02

Pos logit contributions
imm+0.059
 tal+0.053
iest+0.051
ww+0.047
boat+0.046
Neg logit contributions
 wasting-0.067
 fighting-0.064
 grounded-0.060
otion-0.060
 sewing-0.059
Token and
Token ID290
Feature activation+4.08e-02

Pos logit contributions
 tal+0.064
ww+0.064
imm+0.063
 flavor+0.062
iest+0.061
Neg logit contributions
otion-0.039
 wasting-0.038
 fighting-0.038
 sewing-0.034
 grounded-0.033
Token got
Token ID1392
Feature activation+9.76e-03

Pos logit contributions
imm+0.091
iest+0.088
 tal+0.086
umm+0.083
ww+0.082
Neg logit contributions
 fighting-0.056
 wasting-0.055
 grounded-0.049
otion-0.047
 sewing-0.043
Token his
Token ID465
Feature activation+7.19e-02

Pos logit contributions
imm+0.017
 tal+0.017
boat+0.017
 flavor+0.017
bye+0.016
Neg logit contributions
otion-0.016
 wasting-0.016
 fighting-0.015
 grounded-0.015
 sewing-0.014
Token fishing
Token ID12478
Feature activation+9.97e-02

Pos logit contributions
imm+0.116
oc+0.100
iest+0.098
ww+0.096
boat+0.094
Neg logit contributions
 fighting-0.140
 wasting-0.131
 sewing-0.127
 twins-0.120
 grounded-0.116
Token rod
Token ID15299
Feature activation+4.14e-02

Pos logit contributions
imm+0.143
ww+0.135
iest+0.128
bye+0.124
 avail+0.120
Neg logit contributions
 fighting-0.172
 sewing-0.164
 wasting-0.152
 living-0.150
 grounded-0.145
Token.
Token ID13
Feature activation+3.33e-02

Pos logit contributions
ww+0.077
imm+0.077
 tal+0.075
 flavor+0.073
bye+0.072
Neg logit contributions
otion-0.062
 fighting-0.061
 wasting-0.060
 sewing-0.056
 grounded-0.053
Token He
Token ID679
Feature activation+5.47e-02

Pos logit contributions
iest+0.057
imm+0.057
boat+0.055
ww+0.053
 tal+0.053
Neg logit contributions
otion-0.058
 wasting-0.055
 sewing-0.054
 fighting-0.054
 Why-0.050
Token cast
Token ID3350
Feature activation+2.36e-02

Pos logit contributions
imm+0.111
iest+0.109
 tal+0.108
ww+0.108
bye+0.107
Neg logit contributions
 fighting-0.074
 wasting-0.074
 grounded-0.066
 sewing-0.060
otion-0.060
Token the
Token ID262
Feature activation+5.18e-02

Pos logit contributions
bye+0.035
imm+0.035
 flavor+0.034
ww+0.034
boat+0.034
Neg logit contributions
otion-0.045
 wasting-0.043
 fighting-0.042
 grounded-0.040
 sewing-0.040
Token Lily
Token ID20037
Feature activation+2.67e-02

Pos logit contributions
otion+0.055
 wasting+0.050
Acc+0.047
 sewing+0.047
 grounded+0.047
Neg logit contributions
 flavor-0.042
ww-0.041
bye-0.038
 flavour-0.037
boat-0.037
Token!
Token ID0
Feature activation+5.39e-05

Pos logit contributions
boat+0.040
 flavor+0.039
imm+0.039
 tal+0.038
iest+0.038
Neg logit contributions
 fighting-0.050
otion-0.048
 wasting-0.048
 grounded-0.044
 sewing-0.044
Token I
Token ID314
Feature activation+2.16e-02

Pos logit contributions
 flavor+0.000
boat+0.000
 tal+0.000
imm+0.000
bye+0.000
Neg logit contributions
otion-0.000
 wasting-0.000
 fighting-0.000
 grounded-0.000
 sewing-0.000
Token admire
Token ID21099
Feature activation+1.10e-02

Pos logit contributions
imm+0.041
 tal+0.041
 flavor+0.040
boat+0.040
bye+0.039
Neg logit contributions
otion-0.031
 wasting-0.030
 grounded-0.029
 fighting-0.029
osing-0.026
Token your
Token ID534
Feature activation+4.13e-02

Pos logit contributions
imm+0.021
boat+0.021
 flavor+0.020
 tal+0.020
bye+0.020
Neg logit contributions
otion-0.017
 wasting-0.017
 fighting-0.016
 grounded-0.015
 sewing-0.014
Token fishing
Token ID12478
Feature activation+9.97e-02

Pos logit contributions
imm+0.057
boat+0.051
 tal+0.047
ww+0.046
iest+0.046
Neg logit contributions
 fighting-0.091
 wasting-0.089
 grounded-0.080
otion-0.078
 sewing-0.078
Token skills
Token ID4678
Feature activation+2.47e-02

Pos logit contributions
imm+0.133
 tal+0.125
ww+0.116
bye+0.111
iest+0.107
Neg logit contributions
 fighting-0.188
 wasting-0.180
 grounded-0.164
 sewing-0.164
 twins-0.161
Token.
Token ID13
Feature activation+1.28e-02

Pos logit contributions
 tal+0.043
imm+0.041
 flavor+0.041
boat+0.040
ww+0.039
Neg logit contributions
otion-0.043
 wasting-0.040
 fighting-0.039
 grounded-0.037
osing-0.036
Token You
Token ID921
Feature activation+1.65e-02

Pos logit contributions
 flavor+0.024
imm+0.024
boat+0.024
 tal+0.024
iest+0.023
Neg logit contributions
otion-0.020
 wasting-0.019
 fighting-0.018
 grounded-0.017
 sewing-0.016
Token caught
Token ID4978
Feature activation+8.75e-03

Pos logit contributions
imm+0.036
 flavor+0.036
 tal+0.036
boat+0.036
bye+0.035
Neg logit contributions
otion-0.020
 wasting-0.019
 fighting-0.018
 grounded-0.018
osing-0.016
Token a
Token ID257
Feature activation+7.37e-02

Pos logit contributions
imm+0.015
boat+0.015
 flavor+0.015
 tal+0.014
bye+0.014
Neg logit contributions
otion-0.015
 wasting-0.015
 fighting-0.014
 grounded-0.013
 sewing-0.013
Token and
Token ID290
Feature activation+2.19e-02

Pos logit contributions
 flavor+0.007
boat+0.007
imm+0.006
 tal+0.006
bye+0.006
Neg logit contributions
otion-0.006
 wasting-0.006
 fighting-0.005
 grounded-0.005
 sewing-0.005
Token decided
Token ID3066
Feature activation+2.40e-04

Pos logit contributions
imm+0.041
 flavor+0.041
 tal+0.041
iest+0.040
ww+0.038
Neg logit contributions
 wasting-0.033
 fighting-0.033
otion-0.033
 grounded-0.031
osing-0.028
Token to
Token ID284
Feature activation+3.92e-02

Pos logit contributions
 flavor+0.000
imm+0.000
boat+0.000
 tal+0.000
bye+0.000
Neg logit contributions
otion-0.001
 wasting-0.000
 fighting-0.000
 grounded-0.000
 sewing-0.000
Token take
Token ID1011
Feature activation+5.37e-02

Pos logit contributions
imm+0.078
iest+0.071
ww+0.071
 tal+0.070
 flavor+0.068
Neg logit contributions
 fighting-0.063
 wasting-0.061
otion-0.059
 grounded-0.058
 hey-0.051
Token a
Token ID257
Feature activation+6.61e-02

Pos logit contributions
imm+0.140
boat+0.130
iest+0.126
 flavor+0.124
bye+0.121
Neg logit contributions
 fighting-0.049
 wasting-0.045
 grounded-0.041
otion-0.037
 sewing-0.033
Token closer
Token ID5699
Feature activation+9.91e-02

Pos logit contributions
imm+0.148
umm+0.127
bye+0.121
iest+0.121
 tal+0.120
Neg logit contributions
 fighting-0.092
 wasting-0.087
otion-0.081
 sewing-0.081
 crying-0.079
Token look
Token ID804
Feature activation-5.02e-03

Pos logit contributions
imm+0.235
umm+0.235
ww+0.218
bye+0.216
eter+0.216
Neg logit contributions
otion-0.071
 fighting-0.067
 crying-0.058
 weeping-0.047
 downstairs-0.047
Token.
Token ID13
Feature activation+1.18e-02

Pos logit contributions
otion+0.011
 wasting+0.010
 fighting+0.009
 grounded+0.009
 sewing+0.009
Neg logit contributions
 flavor-0.007
boat-0.007
 tal-0.007
imm-0.007
bye-0.006
Token He
Token ID679
Feature activation+3.73e-02

Pos logit contributions
 flavor+0.017
imm+0.017
iest+0.017
boat+0.017
 tal+0.016
Neg logit contributions
otion-0.024
 wasting-0.023
 fighting-0.022
 grounded-0.021
 sewing-0.021
Token decided
Token ID3066
Feature activation-1.18e-02

Pos logit contributions
imm+0.072
iest+0.072
 flavor+0.070
bye+0.069
ww+0.069
Neg logit contributions
 fighting-0.053
 wasting-0.052
 grounded-0.050
otion-0.048
 sewing-0.045
Token to
Token ID284
Feature activation+3.41e-02

Pos logit contributions
otion+0.029
 wasting+0.027
 grounded+0.025
 fighting+0.025
 sewing+0.025
Neg logit contributions
 flavor-0.013
boat-0.012
 tal-0.012
bye-0.012
imm-0.011
Token,
Token ID11
Feature activation+4.64e-03

Pos logit contributions
 flavor+0.027
imm+0.027
 tal+0.026
boat+0.026
bye+0.024
Neg logit contributions
otion-0.040
 wasting-0.037
 fighting-0.037
 grounded-0.034
osing-0.033
Token dinner
Token ID8073
Feature activation+5.83e-02

Pos logit contributions
imm+0.007
 tal+0.007
 flavor+0.007
boat+0.007
bye+0.007
Neg logit contributions
otion-0.009
 wasting-0.009
 fighting-0.008
 grounded-0.008
 sewing-0.008
Token time
Token ID640
Feature activation+2.66e-02

Pos logit contributions
 tal+0.111
boat+0.108
imm+0.108
His+0.099
ull+0.098
Neg logit contributions
 wasting-0.086
otion-0.085
 fighting-0.082
 grounded-0.072
 sewing-0.071
Token!"
Token ID2474
Feature activation+3.83e-02

Pos logit contributions
imm+0.040
boat+0.038
 tal+0.036
 flavor+0.036
iest+0.035
Neg logit contributions
otion-0.052
 wasting-0.052
 fighting-0.051
 grounded-0.047
 sewing-0.047
Token exclaimed
Token ID33552
Feature activation+1.83e-02

Pos logit contributions
imm+0.063
 tal+0.059
iest+0.058
boat+0.057
 flavor+0.056
Neg logit contributions
otion-0.070
 fighting-0.069
 wasting-0.068
 grounded-0.062
 sewing-0.060
Token Nem
Token ID22547
Feature activation+9.72e-02

Pos logit contributions
imm+0.021
boat+0.020
 tal+0.020
 flavor+0.019
ww+0.019
Neg logit contributions
otion-0.043
 wasting-0.042
 fighting-0.041
 sewing-0.038
 grounded-0.038
Tokeno
Token ID78
Feature activation+5.84e-02

Pos logit contributions
 seas+0.192
 seaw+0.192
 avail+0.191
iest+0.188
 pearl+0.187
Neg logit contributions
 crying-0.103
 fighting-0.095
oled-0.093
She-0.093
 Why-0.091
Token.
Token ID13
Feature activation+3.52e-02

Pos logit contributions
ww+0.119
iest+0.117
 flavor+0.116
boat+0.112
 tal+0.111
Neg logit contributions
 fighting-0.076
 crying-0.075
otion-0.073
 wasting-0.071
 sewing-0.070
Token
Token ID198
Feature activation+3.63e-02

Pos logit contributions
iest+0.085
boat+0.083
imm+0.082
 tal+0.082
ww+0.081
Neg logit contributions
otion-0.040
 fighting-0.035
 wasting-0.034
 sewing-0.033
 crying-0.030
Token
Token ID198
Feature activation+2.05e-02

Pos logit contributions
imm+0.073
 flavor+0.072
 tal+0.072
boat+0.071
iest+0.070
Neg logit contributions
otion-0.051
 fighting-0.044
 wasting-0.043
osing-0.042
 sewing-0.042
TokenBut
Token ID1537
Feature activation+2.63e-02

Pos logit contributions
 tal+0.043
imm+0.042
 flavor+0.041
iest+0.040
boat+0.039
Neg logit contributions
otion-0.027
 wasting-0.026
 grounded-0.025
 fighting-0.024
osing-0.024
Token,
Token ID11
Feature activation-1.33e-03

Pos logit contributions
imm+0.064
 tal+0.063
bye+0.057
 flavor+0.056
boat+0.056
Neg logit contributions
otion-0.095
 wasting-0.094
 fighting-0.091
 grounded-0.086
 sewing-0.085
Token and
Token ID290
Feature activation+1.56e-02

Pos logit contributions
otion+0.002
 wasting+0.002
 fighting+0.002
 grounded+0.002
 sewing+0.002
Neg logit contributions
 flavor-0.002
boat-0.002
 tal-0.002
imm-0.002
bye-0.002
Token we
Token ID356
Feature activation-2.37e-02

Pos logit contributions
imm+0.027
boat+0.026
 tal+0.025
 flavor+0.025
bye+0.025
Neg logit contributions
otion-0.027
 wasting-0.027
 fighting-0.025
 grounded-0.024
 sewing-0.024
Token can
Token ID460
Feature activation+2.33e-02

Pos logit contributions
otion+0.038
 wasting+0.034
 sewing+0.032
Acc+0.032
 fighting+0.031
Neg logit contributions
 flavor-0.045
boat-0.044
 tal-0.042
 flavour-0.041
imm-0.041
Token catch
Token ID4929
Feature activation+2.64e-02

Pos logit contributions
imm+0.042
 tal+0.041
boat+0.039
iest+0.039
ww+0.039
Neg logit contributions
otion-0.039
 wasting-0.039
 fighting-0.038
 grounded-0.035
 sewing-0.033
Token one
Token ID530
Feature activation+9.66e-02

Pos logit contributions
imm+0.048
boat+0.046
bye+0.044
 flavor+0.044
iest+0.044
Neg logit contributions
 wasting-0.043
otion-0.042
 fighting-0.042
 grounded-0.038
 sewing-0.036
Token.
Token ID13
Feature activation+1.48e-02

Pos logit contributions
imm+0.203
 tal+0.183
oy+0.165
icol+0.160
bye+0.160
Neg logit contributions
 wasting-0.118
 fighting-0.114
otion-0.107
osing-0.094
 grounded-0.094
Token Do
Token ID2141
Feature activation+1.02e-02

Pos logit contributions
imm+0.028
 flavor+0.028
boat+0.027
 tal+0.027
iest+0.027
Neg logit contributions
otion-0.024
 wasting-0.022
 fighting-0.021
 grounded-0.020
 sewing-0.019
Token you
Token ID345
Feature activation+5.58e-03

Pos logit contributions
boat+0.022
imm+0.022
 tal+0.021
 flavor+0.021
iest+0.020
Neg logit contributions
otion-0.014
 wasting-0.013
 fighting-0.012
 grounded-0.011
osing-0.011
Token want
Token ID765
Feature activation+4.49e-02

Pos logit contributions
 flavor+0.012
imm+0.012
boat+0.012
 tal+0.011
bye+0.011
Neg logit contributions
otion-0.008
 wasting-0.007
 fighting-0.007
 grounded-0.006
osing-0.006
Token to
Token ID284
Feature activation+4.36e-02

Pos logit contributions
imm+0.101
boat+0.091
iest+0.084
umm+0.083
 tal+0.082
Neg logit contributions
 fighting-0.061
 wasting-0.060
 sewing-0.056
otion-0.055
 grounded-0.052
Token He
Token ID679
Feature activation+4.11e-02

Pos logit contributions
 flavor+0.042
iest+0.042
imm+0.041
boat+0.041
 tal+0.039
Neg logit contributions
otion-0.045
 wasting-0.043
 fighting-0.042
 grounded-0.040
osing-0.040
Token wanted
Token ID2227
Feature activation+4.06e-02

Pos logit contributions
imm+0.071
 flavor+0.071
iest+0.070
 tal+0.070
ww+0.069
Neg logit contributions
 fighting-0.062
 wasting-0.061
otion-0.059
 grounded-0.057
 sewing-0.053
Token to
Token ID284
Feature activation+4.72e-02

Pos logit contributions
imm+0.086
boat+0.081
ww+0.077
 tal+0.075
bye+0.074
Neg logit contributions
 fighting-0.059
 wasting-0.057
otion-0.053
 sewing-0.051
 crying-0.048
Token get
Token ID651
Feature activation+2.03e-02

Pos logit contributions
imm+0.094
ww+0.089
iest+0.086
boat+0.084
 tal+0.083
Neg logit contributions
 fighting-0.066
 wasting-0.064
otion-0.063
 grounded-0.056
 sewing-0.056
Token a
Token ID257
Feature activation+8.56e-02

Pos logit contributions
imm+0.037
 flavor+0.035
 tal+0.035
boat+0.034
ww+0.033
Neg logit contributions
otion-0.032
 wasting-0.032
 fighting-0.032
 grounded-0.030
 sewing-0.028
Token closer
Token ID5699
Feature activation+9.61e-02

Pos logit contributions
imm+0.177
umm+0.157
 tal+0.149
cream+0.141
boat+0.139
Neg logit contributions
 fighting-0.104
 sewing-0.104
 crying-0.101
 salon-0.098
 backstage-0.097
Token look
Token ID804
Feature activation+2.60e-02

Pos logit contributions
imm+0.230
cream+0.229
umm+0.222
iest+0.213
 flavours+0.212
Neg logit contributions
otion-0.060
 fighting-0.058
 crying-0.053
 weeping-0.043
 what-0.040
Token,
Token ID11
Feature activation+1.65e-02

Pos logit contributions
 flavor+0.047
 tal+0.047
imm+0.047
boat+0.046
bye+0.045
Neg logit contributions
otion-0.041
 wasting-0.038
 fighting-0.038
 grounded-0.035
osing-0.034
Token so
Token ID523
Feature activation+4.52e-02

Pos logit contributions
imm+0.028
boat+0.027
 flavor+0.027
iest+0.027
 tal+0.026
Neg logit contributions
otion-0.028
 wasting-0.028
 fighting-0.027
 grounded-0.025
 sewing-0.025
Token he
Token ID339
Feature activation+4.05e-02

Pos logit contributions
imm+0.065
boat+0.059
 tal+0.057
 flavor+0.056
iest+0.053
Neg logit contributions
 fighting-0.089
 wasting-0.088
otion-0.087
 crying-0.082
 grounded-0.081
Token walked
Token ID6807
Feature activation+7.57e-03

Pos logit contributions
 tal+0.071
 flavor+0.070
iest+0.070
imm+0.070
bye+0.067
Neg logit contributions
 wasting-0.060
 fighting-0.059
 grounded-0.059
otion-0.058
 sewing-0.054
Token Bob
Token ID5811
Feature activation+3.11e-02

Pos logit contributions
orse+0.131
eed+0.128
 lifetime+0.125
imm+0.124
iest+0.123
Neg logit contributions
 fighting-0.104
 wasting-0.093
 them-0.091
 grounded-0.088
 her-0.086
Tokeno
Token ID78
Feature activation+1.29e-03

Pos logit contributions
imm+0.037
boat+0.034
 tal+0.034
 flavor+0.033
ww+0.033
Neg logit contributions
 wasting-0.065
otion-0.065
 fighting-0.063
 grounded-0.061
 sewing-0.060
Token a
Token ID257
Feature activation+5.08e-02

Pos logit contributions
 flavor+0.002
imm+0.002
boat+0.002
 tal+0.002
bye+0.002
Neg logit contributions
otion-0.002
 wasting-0.002
 fighting-0.002
 grounded-0.002
 sewing-0.002
Token big
Token ID1263
Feature activation+1.58e-02

Pos logit contributions
imm+0.094
bye+0.084
boat+0.083
oy+0.083
iest+0.081
Neg logit contributions
 sewing-0.082
 wasting-0.080
 crying-0.076
 fighting-0.075
otion-0.075
Token hug
Token ID16225
Feature activation+2.00e-02

Pos logit contributions
imm+0.028
boat+0.027
 flavor+0.027
 tal+0.026
iest+0.026
Neg logit contributions
otion-0.026
 wasting-0.025
 fighting-0.024
 grounded-0.023
 sewing-0.023
Token and
Token ID290
Feature activation+9.61e-02

Pos logit contributions
imm+0.035
 tal+0.035
 flavor+0.034
ww+0.033
boat+0.033
Neg logit contributions
otion-0.034
 wasting-0.032
 fighting-0.031
 grounded-0.030
 sewing-0.029
Token put
Token ID1234
Feature activation+4.48e-02

Pos logit contributions
imm+0.237
boat+0.212
umm+0.208
iest+0.203
eed+0.196
Neg logit contributions
 wasting-0.107
 fighting-0.093
 cleans-0.091
 twins-0.090
 grounded-0.090
Token him
Token ID683
Feature activation-1.22e-02

Pos logit contributions
imm+0.087
ww+0.080
bye+0.080
 flavor+0.080
boat+0.079
Neg logit contributions
 fighting-0.060
otion-0.060
 wasting-0.058
 grounded-0.056
 sewing-0.052
Token back
Token ID736
Feature activation+3.01e-04

Pos logit contributions
otion+0.021
 wasting+0.019
 fighting+0.018
 grounded+0.018
osing+0.017
Neg logit contributions
 flavor-0.022
boat-0.021
 tal-0.021
imm-0.021
bye-0.020
Token in
Token ID287
Feature activation+2.23e-02

Pos logit contributions
 flavor+0.001
boat+0.001
 tal+0.001
imm+0.001
bye+0.001
Neg logit contributions
otion-0.000
 wasting-0.000
 fighting-0.000
 grounded-0.000
 sewing-0.000
Token the
Token ID262
Feature activation-1.50e-02

Pos logit contributions
imm+0.042
bye+0.040
ww+0.039
boat+0.038
iest+0.038
Neg logit contributions
 wasting-0.036
 fighting-0.035
otion-0.035
 sewing-0.034
 grounded-0.032
Token He
Token ID679
Feature activation+4.35e-02

Pos logit contributions
 flavor+0.032
imm+0.032
iest+0.032
boat+0.032
 tal+0.030
Neg logit contributions
otion-0.041
 wasting-0.040
 fighting-0.039
 grounded-0.037
osing-0.036
Token wanted
Token ID2227
Feature activation+3.94e-02

Pos logit contributions
imm+0.074
 flavor+0.074
iest+0.073
 tal+0.073
bye+0.072
Neg logit contributions
 fighting-0.065
 wasting-0.065
otion-0.063
 grounded-0.061
 sewing-0.057
Token to
Token ID284
Feature activation+4.74e-02

Pos logit contributions
imm+0.079
boat+0.075
ww+0.071
 tal+0.069
bye+0.069
Neg logit contributions
 fighting-0.059
 wasting-0.059
otion-0.055
 sewing-0.052
 grounded-0.050
Token get
Token ID651
Feature activation+1.93e-02

Pos logit contributions
imm+0.094
ww+0.088
iest+0.086
boat+0.083
 tal+0.083
Neg logit contributions
 fighting-0.068
 wasting-0.066
otion-0.066
 grounded-0.058
 sewing-0.057
Token a
Token ID257
Feature activation+8.57e-02

Pos logit contributions
imm+0.035
 flavor+0.034
 tal+0.033
boat+0.033
bye+0.032
Neg logit contributions
otion-0.031
 wasting-0.031
 fighting-0.030
 grounded-0.028
 sewing-0.027
Token closer
Token ID5699
Feature activation+9.58e-02

Pos logit contributions
imm+0.180
umm+0.159
 tal+0.149
cream+0.142
boat+0.141
Neg logit contributions
 fighting-0.102
 sewing-0.100
 crying-0.099
 backstage-0.094
 salon-0.092
Token look
Token ID804
Feature activation+2.28e-02

Pos logit contributions
imm+0.224
cream+0.223
umm+0.217
oc+0.206
 flavors+0.205
Neg logit contributions
otion-0.065
 fighting-0.061
 crying-0.057
 weeping-0.048
 what-0.043
Token,
Token ID11
Feature activation+1.17e-02

Pos logit contributions
 flavor+0.040
imm+0.039
 tal+0.039
boat+0.038
bye+0.037
Neg logit contributions
otion-0.038
 wasting-0.036
 fighting-0.035
 grounded-0.033
osing-0.032
Token so
Token ID523
Feature activation+4.31e-02

Pos logit contributions
imm+0.019
 flavor+0.019
boat+0.019
 tal+0.018
iest+0.018
Neg logit contributions
otion-0.021
 wasting-0.021
 fighting-0.020
 grounded-0.019
 sewing-0.018
Token he
Token ID339
Feature activation+4.30e-02

Pos logit contributions
imm+0.057
boat+0.051
 flavor+0.050
 tal+0.050
iest+0.047
Neg logit contributions
 wasting-0.089
 fighting-0.089
otion-0.088
 grounded-0.083
 crying-0.080
Token walked
Token ID6807
Feature activation+8.17e-03

Pos logit contributions
 flavor+0.074
 tal+0.074
imm+0.074
iest+0.073
bye+0.071
Neg logit contributions
 wasting-0.064
 grounded-0.063
 fighting-0.063
otion-0.062
 sewing-0.058
Token old
Token ID1468
Feature activation+1.12e-02

Pos logit contributions
otion+0.013
 wasting+0.012
 fighting+0.011
 grounded+0.011
osing+0.011
Neg logit contributions
 flavor-0.010
boat-0.009
 tal-0.009
imm-0.009
bye-0.009
Token lady
Token ID10846
Feature activation-9.64e-03

Pos logit contributions
imm+0.018
 tal+0.017
boat+0.017
 flavor+0.017
iest+0.016
Neg logit contributions
otion-0.021
 wasting-0.020
 fighting-0.019
 grounded-0.018
 sewing-0.018
Token with
Token ID351
Feature activation+9.80e-03

Pos logit contributions
otion+0.019
 wasting+0.018
 fighting+0.017
 grounded+0.017
 sewing+0.016
Neg logit contributions
 flavor-0.014
boat-0.014
imm-0.014
 tal-0.014
bye-0.013
Token a
Token ID257
Feature activation+3.06e-02

Pos logit contributions
imm+0.016
boat+0.016
 flavor+0.016
bye+0.016
 tal+0.016
Neg logit contributions
otion-0.017
 wasting-0.017
 fighting-0.016
 grounded-0.015
 sewing-0.015
Token mis
Token ID2984
Feature activation+1.96e-02

Pos logit contributions
imm+0.049
bye+0.046
boat+0.046
 flavor+0.044
iest+0.044
Neg logit contributions
otion-0.054
 wasting-0.054
 fighting-0.052
 sewing-0.051
 grounded-0.050
Tokenchie
Token ID3043
Feature activation+9.58e-02

Pos logit contributions
 flavor+0.035
 tal+0.033
imm+0.033
boat+0.033
 carrot+0.032
Neg logit contributions
otion-0.032
 wasting-0.030
 grounded-0.029
 fighting-0.028
osing-0.028
Tokenvous
Token ID31222
Feature activation+2.83e-02

Pos logit contributions
eed+0.132
 Crab+0.130
 carrot+0.129
umm+0.127
imm+0.127
Neg logit contributions
otion-0.164
 grounded-0.160
 wasting-0.148
osing-0.148
 fighting-0.144
Token tw
Token ID665
Feature activation+2.62e-02

Pos logit contributions
imm+0.049
boat+0.048
 flavor+0.046
bye+0.045
 tal+0.045
Neg logit contributions
otion-0.049
 wasting-0.046
 fighting-0.045
 grounded-0.042
 sewing-0.042
Tokeninkle
Token ID19894
Feature activation-2.95e-03

Pos logit contributions
 flavor+0.040
bye+0.038
boat+0.038
 tal+0.036
imm+0.035
Neg logit contributions
otion-0.049
 wasting-0.045
 sewing-0.044
 grounded-0.042
osing-0.042
Token in
Token ID287
Feature activation+3.52e-03

Pos logit contributions
otion+0.005
 wasting+0.005
 fighting+0.005
 grounded+0.005
 sewing+0.004
Neg logit contributions
 flavor-0.005
boat-0.005
imm-0.005
 tal-0.005
bye-0.005
Token her
Token ID607
Feature activation+2.50e-02

Pos logit contributions
 flavor+0.006
imm+0.006
boat+0.006
 tal+0.006
bye+0.006
Neg logit contributions
otion-0.006
 wasting-0.006
 fighting-0.005
 grounded-0.005
 sewing-0.005
Token room
Token ID2119
Feature activation-4.46e-02

Pos logit contributions
otion+0.023
 wasting+0.020
osing+0.019
 grounded+0.019
 fighting+0.018
Neg logit contributions
 flavor-0.023
 tal-0.022
boat-0.022
bye-0.022
imm-0.021
Token.
Token ID13
Feature activation-5.38e-02

Pos logit contributions
otion+0.117
 wasting+0.110
Acc+0.110
osing+0.109
 grounded+0.109
Neg logit contributions
 flavor-0.032
boat-0.025
bye-0.025
imm-0.024
iest-0.023
Token She
Token ID1375
Feature activation-7.51e-02

Pos logit contributions
otion+0.095
 wasting+0.089
 grounded+0.089
pping+0.087
osing+0.084
Neg logit contributions
 His-0.081
 flavor-0.074
 tum-0.073
 tal-0.073
 He-0.072
Token sees
Token ID7224
Feature activation-5.50e-02

Pos logit contributions
otion+0.148
Acc+0.134
osing+0.126
 wasting+0.119
ivated+0.118
Neg logit contributions
 tal-0.098
oc-0.096
--0.087
 carrot-0.086
 trick-0.086
Token the
Token ID262
Feature activation-4.62e-02

Pos logit contributions
Acc+0.119
 grounded+0.112
otion+0.112
assing+0.108
osing+0.105
Neg logit contributions
 flavor-0.062
 fish-0.060
 his-0.057
 carrot-0.054
 he-0.052
Token twins
Token ID20345
Feature activation-1.05e-01

Pos logit contributions
otion+0.090
osing+0.085
Acc+0.080
 wasting+0.074
years+0.072
Neg logit contributions
 flavor-0.077
 carrot-0.069
boat-0.069
 sound-0.068
iest-0.066
Token slapping
Token ID48966
Feature activation-1.77e-02

Pos logit contributions
Acc+0.196
Girls+0.179
Scar+0.174
years+0.172
aila+0.172
Neg logit contributions
 sound-0.127
 flavor-0.125
 dive-0.125
 he-0.114
!-0.114
Token each
Token ID1123
Feature activation-1.54e-03

Pos logit contributions
otion+0.032
 wasting+0.030
 grounded+0.029
Acc+0.028
osing+0.028
Neg logit contributions
 flavor-0.029
boat-0.028
imm-0.027
 tal-0.027
iest-0.026
Token other
Token ID584
Feature activation-2.82e-02

Pos logit contributions
otion+0.003
 wasting+0.003
 fighting+0.003
 grounded+0.002
 sewing+0.002
Neg logit contributions
 flavor-0.003
boat-0.002
 tal-0.002
imm-0.002
bye-0.002
Token and
Token ID290
Feature activation-3.38e-02

Pos logit contributions
otion+0.060
 wasting+0.056
Acc+0.054
 grounded+0.054
osing+0.053
Neg logit contributions
 flavor-0.037
boat-0.036
 tal-0.034
bye-0.033
iest-0.033
Token the
Token ID262
Feature activation-4.67e-02

Pos logit contributions
otion+0.059
osing+0.053
Acc+0.051
 grounded+0.049
 wasting+0.046
Neg logit contributions
 flavor-0.057
 tal-0.055
boat-0.052
 fish-0.050
 flavour-0.050
Token hall
Token ID6899
Feature activation-6.12e-02

Pos logit contributions
otion+0.129
osing+0.114
ivated+0.102
Acc+0.098
oled+0.098
Neg logit contributions
 place-0.101
 flavor-0.094
 rod-0.094
 carrot-0.093
 fish-0.090
Token.
Token ID13
Feature activation-3.99e-02

Pos logit contributions
otion+0.151
Acc+0.144
 wasting+0.142
 grounded+0.141
 sewing+0.138
Neg logit contributions
boat-0.044
 flavor-0.044
bye-0.044
 sound-0.041
imm-0.037
Token She
Token ID1375
Feature activation-7.16e-02

Pos logit contributions
otion+0.064
 wasting+0.062
 grounded+0.059
Acc+0.055
osing+0.055
Neg logit contributions
 flavor-0.068
 tal-0.067
bye-0.067
 His-0.067
ww-0.063
Token sees
Token ID7224
Feature activation-4.79e-02

Pos logit contributions
otion+0.136
Acc+0.129
osing+0.117
 wasting+0.112
ivated+0.107
Neg logit contributions
oc-0.097
 tal-0.096
 flavor-0.092
 trick-0.089
--0.088
Token the
Token ID262
Feature activation-7.31e-02

Pos logit contributions
Acc+0.096
 grounded+0.095
otion+0.094
 wasting+0.087
osing+0.085
Neg logit contributions
 flavor-0.061
iest-0.053
 fish-0.053
 Joe-0.052
 his-0.051
Token twins
Token ID20345
Feature activation-1.04e-01

Pos logit contributions
Acc+0.147
otion+0.145
osing+0.144
years+0.133
ivated+0.128
Neg logit contributions
 flavor-0.110
 sound-0.103
 rod-0.101
 fish-0.100
 trick-0.098
Token fighting
Token ID4330
Feature activation-4.09e-02

Pos logit contributions
Acc+0.222
Girls+0.201
years+0.195
 folders+0.193
Scar+0.192
Neg logit contributions
 dive-0.099
 sound-0.099
 flavor-0.099
!-0.095
 he-0.091
Token over
Token ID625
Feature activation-4.17e-02

Pos logit contributions
otion+0.089
Acc+0.087
 wasting+0.086
osing+0.085
 sewing+0.084
Neg logit contributions
 flavor-0.045
boat-0.042
 sound-0.039
imm-0.037
 trick-0.037
Token the
Token ID262
Feature activation-6.49e-02

Pos logit contributions
otion+0.094
 grounded+0.086
 wasting+0.083
osing+0.083
Acc+0.082
Neg logit contributions
 flavor-0.055
 his-0.044
 fish-0.044
 tal-0.044
boat-0.044
Token box
Token ID3091
Feature activation-1.85e-02

Pos logit contributions
otion+0.152
Acc+0.143
osing+0.142
ivated+0.133
years+0.131
Neg logit contributions
 flavor-0.078
 rod-0.072
 trick-0.068
 carrot-0.067
 game-0.067
Token.
Token ID13
Feature activation-2.81e-02

Pos logit contributions
otion+0.040
 wasting+0.039
 grounded+0.037
Acc+0.036
 fighting+0.036
Neg logit contributions
 flavor-0.023
boat-0.022
imm-0.022
 tal-0.021
iest-0.021
Token they
Token ID484
Feature activation-3.78e-02

Pos logit contributions
 flavor+0.002
boat+0.002
imm+0.002
 tal+0.002
bye+0.002
Neg logit contributions
otion-0.002
 wasting-0.002
 fighting-0.002
 grounded-0.002
 sewing-0.002
Token did
Token ID750
Feature activation-3.23e-02

Pos logit contributions
otion+0.075
 wasting+0.065
 sewing+0.065
Acc+0.061
 salon+0.061
Neg logit contributions
 flavor-0.060
bye-0.054
boat-0.052
 flavour-0.052
imm-0.051
Token.
Token ID13
Feature activation-1.74e-02

Pos logit contributions
otion+0.076
 wasting+0.073
 grounded+0.068
 fighting+0.067
Acc+0.067
Neg logit contributions
 flavor-0.035
iest-0.033
boat-0.033
bye-0.032
imm-0.030
Token She
Token ID1375
Feature activation-6.34e-02

Pos logit contributions
otion+0.029
 wasting+0.028
 grounded+0.026
 fighting+0.026
 sewing+0.025
Neg logit contributions
 flavor-0.030
 tal-0.029
bye-0.028
imm-0.028
boat-0.027
Token says
Token ID1139
Feature activation-4.53e-02

Pos logit contributions
otion+0.129
ivated+0.109
osing+0.104
 wasting+0.104
oled+0.104
Neg logit contributions
 carrot-0.089
 flavor-0.085
 tal-0.082
 fish-0.079
oc-0.079
Token they
Token ID484
Feature activation-9.94e-02

Pos logit contributions
assing+0.100
otion+0.100
 grounded+0.097
 wasting+0.097
ivated+0.090
Neg logit contributions
 flavor-0.046
 he-0.042
ww-0.040
 fish-0.039
orse-0.039
Token will
Token ID481
Feature activation-1.07e-02

Pos logit contributions
otion+0.236
ivated+0.212
pering+0.211
 backstage+0.209
 sewing+0.207
Neg logit contributions
 flavor-0.090
 flavour-0.072
bye-0.070
oc-0.069
 fish-0.067
Token not
Token ID407
Feature activation+3.90e-03

Pos logit contributions
otion+0.021
 wasting+0.019
 fighting+0.018
 grounded+0.018
osing+0.017
Neg logit contributions
 flavor-0.017
boat-0.016
 tal-0.016
bye-0.016
imm-0.016
Token have
Token ID423
Feature activation+4.31e-03

Pos logit contributions
 flavor+0.006
boat+0.006
imm+0.006
 tal+0.006
bye+0.006
Neg logit contributions
otion-0.007
 wasting-0.007
 fighting-0.007
 grounded-0.006
 sewing-0.006
Token any
Token ID597
Feature activation+6.85e-03

Pos logit contributions
boat+0.007
imm+0.007
 flavor+0.007
 tal+0.007
bye+0.007
Neg logit contributions
otion-0.008
 wasting-0.008
 fighting-0.007
 grounded-0.007
 sewing-0.007
Token jam
Token ID16853
Feature activation-6.04e-03

Pos logit contributions
boat+0.011
imm+0.010
 tal+0.010
 flavor+0.010
bye+0.010
Neg logit contributions
otion-0.013
 wasting-0.013
 fighting-0.012
 grounded-0.012
 sewing-0.012
Token room
Token ID2119
Feature activation-4.04e-02

Pos logit contributions
otion+0.024
 wasting+0.022
 grounded+0.020
 fighting+0.020
osing+0.020
Neg logit contributions
 flavor-0.025
boat-0.025
imm-0.024
 tal-0.024
iest-0.023
Token.
Token ID13
Feature activation-2.23e-02

Pos logit contributions
otion+0.086
 wasting+0.080
 grounded+0.078
Acc+0.076
osing+0.076
Neg logit contributions
 flavor-0.050
boat-0.047
bye-0.044
imm-0.044
iest-0.044
Token She
Token ID1375
Feature activation-8.60e-02

Pos logit contributions
otion+0.037
 wasting+0.036
 grounded+0.035
 fighting+0.032
osing+0.032
Neg logit contributions
 flavor-0.038
 tal-0.037
 His-0.035
boat-0.035
imm-0.035
Token sees
Token ID7224
Feature activation-4.60e-02

Pos logit contributions
otion+0.176
Acc+0.169
nam+0.156
osing+0.155
Fighting+0.153
Neg logit contributions
 flavor-0.087
 dive-0.086
 flavors-0.083
 fish-0.081
 trick-0.081
Token the
Token ID262
Feature activation-5.88e-02

Pos logit contributions
otion+0.092
Acc+0.091
 grounded+0.090
assing+0.087
osing+0.085
Neg logit contributions
 flavor-0.061
iest-0.051
 fish-0.049
 flavour-0.048
 tal-0.048
Token twins
Token ID20345
Feature activation-9.90e-02

Pos logit contributions
otion+0.118
osing+0.109
Acc+0.105
 wasting+0.099
 grounded+0.097
Neg logit contributions
 flavor-0.096
 carrot-0.083
 flavour-0.082
boat-0.082
iest-0.082
Token fighting
Token ID4330
Feature activation-2.70e-02

Pos logit contributions
Acc+0.187
Girls+0.167
 folders+0.163
years+0.163
aila+0.162
Neg logit contributions
 flavor-0.122
 dive-0.121
 sound-0.112
 fish-0.108
 he-0.107
Token and
Token ID290
Feature activation-4.63e-02

Pos logit contributions
otion+0.053
 wasting+0.050
Acc+0.048
 grounded+0.048
 sewing+0.048
Neg logit contributions
 flavor-0.039
boat-0.037
imm-0.035
bye-0.034
iest-0.034
Token the
Token ID262
Feature activation-4.77e-02

Pos logit contributions
otion+0.078
Acc+0.074
osing+0.072
 grounded+0.070
 sewing+0.064
Neg logit contributions
 flavor-0.076
boat-0.067
 flavour-0.066
 tal-0.065
 fish-0.065
Token beads
Token ID36116
Feature activation-3.40e-02

Pos logit contributions
otion+0.094
osing+0.084
 wasting+0.082
Acc+0.081
 grounded+0.079
Neg logit contributions
 flavor-0.079
boat-0.068
 flavour-0.068
iest-0.066
 tal-0.064
Token on
Token ID319
Feature activation-1.74e-03

Pos logit contributions
otion+0.070
 wasting+0.067
 grounded+0.065
Acc+0.065
 sewing+0.063
Neg logit contributions
boat-0.045
 flavor-0.044
iest-0.042
imm-0.041
 tal-0.040
Token play
Token ID711
Feature activation-9.95e-03

Pos logit contributions
 tal+0.019
imm+0.019
boat+0.019
 flavor+0.018
ww+0.018
Neg logit contributions
otion-0.020
 wasting-0.019
 fighting-0.019
 grounded-0.018
 sewing-0.018
Token outside
Token ID2354
Feature activation-6.29e-03

Pos logit contributions
otion+0.019
 wasting+0.018
 grounded+0.017
 fighting+0.017
osing+0.016
Neg logit contributions
 flavor-0.015
boat-0.015
imm-0.015
 tal-0.014
iest-0.014
Token.
Token ID13
Feature activation+1.08e-02

Pos logit contributions
otion+0.013
 wasting+0.012
 fighting+0.012
 grounded+0.012
 sewing+0.011
Neg logit contributions
 flavor-0.009
boat-0.008
imm-0.008
 tal-0.008
bye-0.008
Token Mom
Token ID11254
Feature activation-6.83e-02

Pos logit contributions
boat+0.018
imm+0.018
 tal+0.018
iest+0.017
 flavor+0.017
Neg logit contributions
otion-0.020
 wasting-0.018
 fighting-0.018
 grounded-0.017
 sewing-0.016
Token says
Token ID1139
Feature activation-3.33e-02

Pos logit contributions
otion+0.147
Acc+0.143
nam+0.143
ivated+0.136
osing+0.131
Neg logit contributions
 carrot-0.074
 flavor-0.071
ah-0.069
 fish-0.065
o-0.062
Token they
Token ID484
Feature activation-9.86e-02

Pos logit contributions
 wasting+0.078
otion+0.078
 grounded+0.076
assing+0.074
Acc+0.073
Neg logit contributions
 flavor-0.036
iest-0.030
 flavour-0.029
bye-0.028
ww-0.028
Token can
Token ID460
Feature activation-9.23e-03

Pos logit contributions
otion+0.232
Acc+0.229
pering+0.209
 wasting+0.206
Girls+0.205
Neg logit contributions
 flavor-0.088
 flavour-0.066
 dive-0.065
 fish-0.064
bye-0.062
Token play
Token ID711
Feature activation-1.61e-02

Pos logit contributions
otion+0.019
 wasting+0.018
 grounded+0.017
 fighting+0.017
osing+0.016
Neg logit contributions
 flavor-0.013
boat-0.013
imm-0.013
bye-0.012
 tal-0.012
Token with
Token ID351
Feature activation-9.12e-03

Pos logit contributions
otion+0.032
 wasting+0.030
 grounded+0.028
 fighting+0.028
osing+0.027
Neg logit contributions
 flavor-0.024
boat-0.023
imm-0.023
iest-0.022
bye-0.022
Token their
Token ID511
Feature activation-2.97e-02

Pos logit contributions
otion+0.017
 wasting+0.016
 grounded+0.015
 fighting+0.015
osing+0.014
Neg logit contributions
 flavor-0.015
 tal-0.014
boat-0.014
imm-0.014
bye-0.014
Token blocks
Token ID7021
Feature activation-3.65e-03

Pos logit contributions
otion+0.058
 wasting+0.052
 grounded+0.050
osing+0.050
Acc+0.048
Neg logit contributions
 flavor-0.051
iest-0.044
boat-0.044
 carrot-0.044
 flavour-0.043
Token broken
Token ID5445
Feature activation-1.30e-02

Pos logit contributions
otion+0.095
osing+0.094
Acc+0.086
years+0.085
 wasting+0.079
Neg logit contributions
 flavor-0.082
 carrot-0.077
 sound-0.076
iest-0.072
 trick-0.070
Token lamp
Token ID20450
Feature activation-3.83e-02

Pos logit contributions
otion+0.024
 wasting+0.022
 grounded+0.021
 fighting+0.020
osing+0.020
Neg logit contributions
 flavor-0.022
boat-0.021
 tal-0.021
iest-0.020
imm-0.020
Token and
Token ID290
Feature activation-5.02e-02

Pos logit contributions
otion+0.074
 wasting+0.069
Acc+0.069
 grounded+0.067
osing+0.066
Neg logit contributions
 flavor-0.055
boat-0.053
imm-0.052
 tal-0.050
iest-0.049
Token the
Token ID262
Feature activation-5.54e-02

Pos logit contributions
otion+0.122
osing+0.113
Acc+0.111
 grounded+0.105
assing+0.105
Neg logit contributions
 his-0.047
 flavor-0.043
 sound-0.042
 he-0.042
 tal-0.041
Token crying
Token ID13774
Feature activation-1.95e-02

Pos logit contributions
otion+0.110
osing+0.104
 wasting+0.088
Acc+0.088
ivated+0.087
Neg logit contributions
 flavor-0.090
 carrot-0.084
 tal-0.082
 sound-0.082
boat-0.078
Token twins
Token ID20345
Feature activation-9.82e-02

Pos logit contributions
otion+0.032
 wasting+0.030
Acc+0.029
 grounded+0.028
osing+0.028
Neg logit contributions
boat-0.034
 flavor-0.034
iest-0.034
imm-0.033
bye-0.032
Token.
Token ID13
Feature activation-4.15e-02

Pos logit contributions
Acc+0.265
Girls+0.255
otion+0.248
years+0.248
Scar+0.247
Neg logit contributions
 flavor-0.030
 sound-0.026
.-0.021
!-0.021
 he-0.021
Token She
Token ID1375
Feature activation-6.42e-02

Pos logit contributions
otion+0.069
 grounded+0.063
 wasting+0.062
osing+0.058
Acc+0.057
Neg logit contributions
 flavor-0.070
 His-0.069
 tal-0.068
bye-0.067
ww-0.065
Token is
Token ID318
Feature activation-4.19e-02

Pos logit contributions
otion+0.133
Acc+0.123
osing+0.114
ivated+0.111
assing+0.109
Neg logit contributions
 tal-0.074
oc-0.070
 flavor-0.068
 His-0.067
 fish-0.066
Token angry
Token ID7954
Feature activation-4.64e-02

Pos logit contributions
otion+0.083
osing+0.071
ains+0.068
Acc+0.067
ories+0.066
Neg logit contributions
 flavor-0.055
 sound-0.051
imm-0.051
 his-0.050
His-0.049
Token and
Token ID290
Feature activation-6.44e-02

Pos logit contributions
otion+0.108
Acc+0.102
 wasting+0.102
 grounded+0.099
 sewing+0.099
Neg logit contributions
bye-0.038
 he-0.038
 flavor-0.037
iest-0.035
 sound-0.034
Token sees
Token ID7224
Feature activation-5.86e-02

Pos logit contributions
otion+0.139
Acc+0.137
nam+0.120
osing+0.118
Fighting+0.117
Neg logit contributions
 trick-0.086
 fish-0.086
oc-0.085
 tal-0.083
 flavor-0.083
Token the
Token ID262
Feature activation-6.54e-02

Pos logit contributions
Acc+0.127
assing+0.118
 grounded+0.117
otion+0.112
oken+0.110
Neg logit contributions
 flavor-0.070
 fish-0.063
iest-0.057
 Bob-0.055
 his-0.055
Token puzzle
Token ID15027
Feature activation-4.05e-02

Pos logit contributions
otion+0.164
Acc+0.154
osing+0.146
years+0.146
 hey+0.144
Neg logit contributions
 flavor-0.069
 piece-0.054
 nut-0.053
 carrot-0.052
 game-0.052
Token and
Token ID290
Feature activation-6.14e-02

Pos logit contributions
otion+0.081
Acc+0.076
 wasting+0.075
 grounded+0.073
 hey+0.072
Neg logit contributions
 flavor-0.057
boat-0.056
iest-0.052
 tal-0.051
imm-0.051
Token the
Token ID262
Feature activation-5.72e-02

Pos logit contributions
otion+0.137
Acc+0.135
oken+0.123
 grounded+0.121
osing+0.120
Neg logit contributions
 his-0.061
 he-0.061
 fish-0.059
 flavor-0.059
 kinds-0.054
Token twins
Token ID20345
Feature activation-9.71e-02

Pos logit contributions
otion+0.132
osing+0.115
Acc+0.114
 grounded+0.108
 wasting+0.104
Neg logit contributions
 flavor-0.078
 tal-0.066
 nut-0.065
 flavour-0.065
 carrot-0.065
Token.
Token ID13
Feature activation-3.08e-02

Pos logit contributions
Acc+0.217
otion+0.201
Girls+0.200
years+0.196
 folders+0.191
Neg logit contributions
 flavor-0.082
 dive-0.076
 sound-0.075
 flavour-0.071
 trick-0.068
Token She
Token ID1375
Feature activation-6.84e-02

Pos logit contributions
otion+0.049
 grounded+0.046
 wasting+0.045
Acc+0.041
osing+0.041
Neg logit contributions
 flavor-0.055
 His-0.053
bye-0.052
 tal-0.051
ww-0.050
Token is
Token ID318
Feature activation-5.03e-02

Pos logit contributions
Acc+0.144
otion+0.142
osing+0.122
ivated+0.122
assing+0.121
Neg logit contributions
 flavor-0.071
 fish-0.069
 trick-0.068
oc-0.064
 tal-0.062
Token not
Token ID407
Feature activation-1.87e-02

Pos logit contributions
otion+0.105
Acc+0.091
osing+0.091
ems+0.089
ains+0.089
Neg logit contributions
 flavor-0.059
 sound-0.057
 his-0.055
 trick-0.055
His-0.049
Token happy
Token ID3772
Feature activation-2.27e-02

Pos logit contributions
otion+0.037
 wasting+0.033
 grounded+0.031
osing+0.031
 fighting+0.030
Neg logit contributions
 flavor-0.028
boat-0.026
imm-0.026
iest-0.025
 tal-0.025
Token broken
Token ID5445
Feature activation-6.77e-03

Pos logit contributions
otion+0.081
osing+0.078
Acc+0.072
years+0.069
 wasting+0.068
Neg logit contributions
 flavor-0.073
 carrot-0.068
 sound-0.066
iest-0.064
 trick-0.063
Token lamp
Token ID20450
Feature activation-4.02e-02

Pos logit contributions
otion+0.013
 wasting+0.012
 fighting+0.011
 grounded+0.011
osing+0.011
Neg logit contributions
 flavor-0.011
boat-0.010
 tal-0.010
imm-0.010
iest-0.010
Token and
Token ID290
Feature activation-5.06e-02

Pos logit contributions
otion+0.078
 wasting+0.073
Acc+0.072
 grounded+0.070
osing+0.070
Neg logit contributions
 flavor-0.057
boat-0.055
imm-0.054
 tal-0.053
iest-0.051
Token the
Token ID262
Feature activation-5.00e-02

Pos logit contributions
otion+0.120
osing+0.109
Acc+0.109
 grounded+0.103
oken+0.103
Neg logit contributions
 his-0.049
 flavor-0.047
 he-0.046
 sound-0.045
 fish-0.040
Token crying
Token ID13774
Feature activation-1.54e-02

Pos logit contributions
otion+0.101
osing+0.096
Acc+0.082
 wasting+0.081
ivated+0.080
Neg logit contributions
 flavor-0.080
 sound-0.074
 carrot-0.073
 tal-0.071
 flavour-0.069
Token twins
Token ID20345
Feature activation-9.66e-02

Pos logit contributions
otion+0.029
 wasting+0.027
 grounded+0.025
Acc+0.025
osing+0.025
Neg logit contributions
 flavor-0.024
boat-0.024
iest-0.023
imm-0.023
bye-0.022
Token.
Token ID13
Feature activation-4.48e-02

Pos logit contributions
Acc+0.243
Girls+0.232
otion+0.232
Scar+0.226
years+0.225
Neg logit contributions
 flavor-0.048
 sound-0.045
 he-0.038
 dive-0.037
!-0.036
Token She
Token ID1375
Feature activation-6.55e-02

Pos logit contributions
otion+0.077
 wasting+0.069
 grounded+0.069
osing+0.064
Acc+0.064
Neg logit contributions
 His-0.075
 flavor-0.073
bye-0.071
 tal-0.068
ww-0.066
Token is
Token ID318
Feature activation-3.84e-02

Pos logit contributions
otion+0.134
Acc+0.124
osing+0.113
ivated+0.112
Fighting+0.110
Neg logit contributions
 tal-0.075
oc-0.072
 flavor-0.071
 His-0.071
--0.068
Token angry
Token ID7954
Feature activation-4.34e-02

Pos logit contributions
otion+0.077
osing+0.065
Acc+0.063
ains+0.063
 wasting+0.062
Neg logit contributions
 flavor-0.051
imm-0.047
 sound-0.045
 tal-0.044
boat-0.044
Token and
Token ID290
Feature activation-6.47e-02

Pos logit contributions
otion+0.101
 wasting+0.095
Acc+0.094
 grounded+0.092
 sewing+0.092
Neg logit contributions
bye-0.037
 he-0.037
 flavor-0.036
iest-0.035
est-0.034
Token sees
Token ID7224
Feature activation-6.07e-02

Pos logit contributions
otion+0.142
Acc+0.132
osing+0.123
nam+0.116
ivated+0.115
Neg logit contributions
 fish-0.093
 tal-0.092
oc-0.091
 carrot-0.091
 trick-0.090
Token the
Token ID262
Feature activation-5.53e-02

Pos logit contributions
Acc+0.127
assing+0.123
 grounded+0.122
otion+0.114
osing+0.112
Neg logit contributions
 flavor-0.070
 fish-0.067
 his-0.065
 carrot-0.062
 he-0.060
Token car
Token ID1097
Feature activation-6.06e-02

Pos logit contributions
otion+0.124
osing+0.118
Acc+0.114
 wasting+0.104
 hey+0.101
Neg logit contributions
 flavor-0.080
boat-0.070
 cone-0.068
 puck-0.067
 carrot-0.065
Token and
Token ID290
Feature activation-4.80e-02

Pos logit contributions
Acc+0.139
otion+0.138
Girls+0.131
years+0.130
 wasting+0.130
Neg logit contributions
boat-0.060
 flavor-0.055
 sound-0.053
 trick-0.050
imm-0.048
Token the
Token ID262
Feature activation-5.20e-02

Pos logit contributions
otion+0.117
osing+0.106
Acc+0.106
 grounded+0.100
oken+0.099
Neg logit contributions
 his-0.046
 flavor-0.045
 fish-0.045
 tal-0.044
 he-0.041
Token twins
Token ID20345
Feature activation-9.65e-02

Pos logit contributions
otion+0.108
osing+0.100
Acc+0.090
 wasting+0.086
ivated+0.084
Neg logit contributions
 flavor-0.085
 tal-0.077
boat-0.076
 carrot-0.073
 puck-0.071
Token.
Token ID13
Feature activation-3.45e-02

Pos logit contributions
Acc+0.244
otion+0.233
Girls+0.232
years+0.231
 folders+0.226
Neg logit contributions
 flavor-0.050
 sound-0.044
 dive-0.039
 cone-0.037
 flavour-0.035
Token She
Token ID1375
Feature activation-6.26e-02

Pos logit contributions
otion+0.055
 grounded+0.051
 wasting+0.051
osing+0.047
Acc+0.047
Neg logit contributions
 flavor-0.060
 His-0.058
 tal-0.058
ww-0.056
bye-0.056
Token is
Token ID318
Feature activation-4.40e-02

Pos logit contributions
otion+0.131
Acc+0.124
osing+0.115
 grounded+0.110
 occurring+0.108
Neg logit contributions
 flavor-0.071
 tal-0.067
oc-0.066
 fish-0.064
 trick-0.064
Token not
Token ID407
Feature activation-1.21e-02

Pos logit contributions
otion+0.083
osing+0.071
Acc+0.068
ains+0.068
ories+0.066
Neg logit contributions
 flavor-0.065
 sound-0.059
 his-0.057
imm-0.057
 trick-0.056
Token happy
Token ID3772
Feature activation-2.07e-02

Pos logit contributions
otion+0.023
 wasting+0.020
 grounded+0.019
 fighting+0.019
osing+0.019
Neg logit contributions
 flavor-0.020
boat-0.019
imm-0.019
 tal-0.018
iest-0.018
Token!
Token ID0
Feature activation+9.15e-03

Pos logit contributions
otion+0.016
 wasting+0.016
 fighting+0.015
 grounded+0.015
 sewing+0.014
Neg logit contributions
 flavor-0.010
boat-0.010
imm-0.010
 tal-0.010
iest-0.010
Token He
Token ID679
Feature activation+6.29e-03

Pos logit contributions
 flavor+0.013
imm+0.013
boat+0.013
 tal+0.012
iest+0.012
Neg logit contributions
otion-0.019
 wasting-0.018
 fighting-0.017
 grounded-0.017
 sewing-0.016
Token asked
Token ID1965
Feature activation+1.94e-03

Pos logit contributions
 flavor+0.010
boat+0.009
imm+0.009
 tal+0.009
bye+0.009
Neg logit contributions
otion-0.012
 wasting-0.011
 fighting-0.011
 grounded-0.011
 sewing-0.010
Token grown
Token ID7334
Feature activation+1.72e-03

Pos logit contributions
 flavor+0.002
boat+0.002
imm+0.002
 tal+0.002
bye+0.002
Neg logit contributions
otion-0.005
 wasting-0.004
 fighting-0.004
 grounded-0.004
 sewing-0.004
Token-
Token ID12
Feature activation-1.16e-02

Pos logit contributions
 flavor+0.002
boat+0.002
 tal+0.002
imm+0.002
bye+0.002
Neg logit contributions
otion-0.003
 wasting-0.003
 fighting-0.003
 grounded-0.003
 sewing-0.003
Tokenups
Token ID4739
Feature activation-9.63e-02

Pos logit contributions
otion+0.024
 wasting+0.022
 fighting+0.021
 grounded+0.021
 sewing+0.020
Neg logit contributions
 flavor-0.017
boat-0.017
bye-0.016
imm-0.016
 tal-0.016
Token to
Token ID284
Feature activation+7.66e-04

Pos logit contributions
otion+0.193
 wasting+0.186
 grounded+0.184
Acc+0.181
 folders+0.176
Neg logit contributions
boat-0.110
 flavor-0.101
iest-0.096
 Joe-0.092
 he-0.092
Token help
Token ID1037
Feature activation+1.33e-02

Pos logit contributions
 flavor+0.001
boat+0.001
imm+0.001
 tal+0.001
bye+0.001
Neg logit contributions
otion-0.001
 wasting-0.001
 fighting-0.001
 grounded-0.001
 sewing-0.001
Token him
Token ID683
Feature activation-8.39e-03

Pos logit contributions
 tal+0.024
imm+0.024
bye+0.024
boat+0.024
 flavor+0.024
Neg logit contributions
otion-0.022
 wasting-0.021
 fighting-0.020
 grounded-0.018
 sewing-0.018
Token wipe
Token ID19916
Feature activation+3.24e-02

Pos logit contributions
otion+0.016
 wasting+0.015
 fighting+0.014
 grounded+0.014
 sewing+0.013
Neg logit contributions
 flavor-0.013
boat-0.013
imm-0.013
 tal-0.013
bye-0.012
Token them
Token ID606
Feature activation+1.84e-02

Pos logit contributions
bye+0.059
imm+0.058
 flavor+0.057
ww+0.056
 tal+0.056
Neg logit contributions
otion-0.050
 wasting-0.049
 fighting-0.047
 grounded-0.044
 sewing-0.042
Token and
Token ID290
Feature activation-4.10e-02

Pos logit contributions
otion+0.134
 wasting+0.124
Acc+0.123
osing+0.121
ivated+0.119
Neg logit contributions
bye-0.061
 flavor-0.061
est-0.056
iest-0.054
boat-0.053
Token selfish
Token ID20363
Feature activation-2.62e-02

Pos logit contributions
otion+0.076
osing+0.058
oled+0.057
 wasting+0.057
 sewing+0.057
Neg logit contributions
 flavor-0.066
bye-0.064
ww-0.062
boat-0.062
cream-0.058
Token.
Token ID13
Feature activation-3.58e-02

Pos logit contributions
otion+0.062
 wasting+0.058
Acc+0.056
 grounded+0.055
osing+0.055
Neg logit contributions
 flavor-0.029
bye-0.027
boat-0.027
iest-0.026
 tal-0.024
Token She
Token ID1375
Feature activation-5.71e-02

Pos logit contributions
otion+0.055
 wasting+0.052
 grounded+0.052
 fighting+0.048
 sewing+0.048
Neg logit contributions
 His-0.062
bye-0.059
 tal-0.059
 flavor-0.058
ww-0.056
Token says
Token ID1139
Feature activation-6.07e-02

Pos logit contributions
otion+0.137
Acc+0.117
ivated+0.116
 wasting+0.116
osing+0.115
Neg logit contributions
 flavor-0.055
 carrot-0.053
 tal-0.051
 trick-0.050
ww-0.048
Token they
Token ID484
Feature activation-9.62e-02

Pos logit contributions
assing+0.151
 grounded+0.149
otion+0.144
 wasting+0.141
oken+0.140
Neg logit contributions
 he-0.051
 flavor-0.041
 fish-0.039
orse-0.035
 carrot-0.033
Token have
Token ID423
Feature activation-2.30e-02

Pos logit contributions
otion+0.232
ivated+0.206
Acc+0.201
pering+0.200
 backstage+0.200
Neg logit contributions
 flavor-0.086
oc-0.072
cream-0.065
 fish-0.063
 flavour-0.062
Token to
Token ID284
Feature activation-4.69e-03

Pos logit contributions
otion+0.060
 wasting+0.053
osing+0.051
 fighting+0.051
 grounded+0.050
Neg logit contributions
 flavor-0.024
 tal-0.021
bye-0.020
boat-0.019
 flavour-0.019
Token share
Token ID2648
Feature activation-2.84e-02

Pos logit contributions
otion+0.009
 wasting+0.009
 fighting+0.008
 grounded+0.008
 sewing+0.008
Neg logit contributions
 flavor-0.007
boat-0.007
 tal-0.007
imm-0.007
bye-0.007
Token their
Token ID511
Feature activation-4.29e-02

Pos logit contributions
otion+0.058
 wasting+0.052
 grounded+0.049
osing+0.048
Acc+0.048
Neg logit contributions
 flavor-0.045
boat-0.040
 tal-0.039
 flavour-0.038
iest-0.038
Token toys
Token ID14958
Feature activation-2.80e-02

Pos logit contributions
otion+0.098
 wasting+0.085
osing+0.082
Acc+0.080
oled+0.079
Neg logit contributions
 flavor-0.064
 flavour-0.052
bye-0.052
 flavors-0.051
 tal-0.051
Token the
Token ID262
Feature activation-3.40e-02

Pos logit contributions
otion+0.049
 wasting+0.044
 grounded+0.043
osing+0.042
 fighting+0.041
Neg logit contributions
 flavor-0.032
 flavour-0.027
 tal-0.027
boat-0.026
bye-0.025
Token music
Token ID2647
Feature activation-9.56e-03

Pos logit contributions
otion+0.073
 wasting+0.066
osing+0.065
Acc+0.062
 hey+0.061
Neg logit contributions
 flavor-0.049
iest-0.043
boat-0.043
bye-0.042
 flavour-0.042
Token.
Token ID13
Feature activation-1.15e-02

Pos logit contributions
otion+0.021
 wasting+0.020
 fighting+0.019
 grounded+0.018
osing+0.018
Neg logit contributions
 flavor-0.012
boat-0.012
imm-0.012
 tal-0.012
bye-0.011
Token She
Token ID1375
Feature activation-6.40e-02

Pos logit contributions
otion+0.024
 wasting+0.022
 grounded+0.021
 fighting+0.021
osing+0.020
Neg logit contributions
 flavor-0.016
 tal-0.015
imm-0.015
bye-0.015
boat-0.015
Token says
Token ID1139
Feature activation-4.92e-02

Pos logit contributions
otion+0.130
ivated+0.110
oled+0.108
assing+0.108
osing+0.105
Neg logit contributions
 flavor-0.088
 carrot-0.086
 flavors-0.078
 fish-0.078
 trick-0.076
Token they
Token ID484
Feature activation-9.60e-02

Pos logit contributions
assing+0.108
otion+0.106
 grounded+0.105
 wasting+0.103
ivated+0.098
Neg logit contributions
 flavor-0.051
 he-0.047
ww-0.043
bye-0.043
orse-0.042
Token can
Token ID460
Feature activation-2.07e-02

Pos logit contributions
otion+0.231
pering+0.218
ivated+0.207
 backstage+0.203
 occurring+0.197
Neg logit contributions
 flavor-0.091
bye-0.071
 flavour-0.070
cream-0.063
 treat-0.062
Token listen
Token ID6004
Feature activation-1.88e-02

Pos logit contributions
otion+0.041
 wasting+0.038
 grounded+0.036
osing+0.034
 fighting+0.034
Neg logit contributions
 flavor-0.032
bye-0.029
boat-0.029
imm-0.028
 flavour-0.028
Token to
Token ID284
Feature activation-1.66e-02

Pos logit contributions
otion+0.046
 wasting+0.043
 fighting+0.040
 grounded+0.040
osing+0.039
Neg logit contributions
 flavor-0.020
bye-0.019
boat-0.018
imm-0.017
 tal-0.017
Token both
Token ID1111
Feature activation-1.15e-02

Pos logit contributions
otion+0.036
 wasting+0.032
osing+0.031
 grounded+0.031
 fighting+0.030
Neg logit contributions
 flavor-0.022
bye-0.021
 tal-0.020
boat-0.019
 flavour-0.019
Token songs
Token ID7259
Feature activation-2.38e-02

Pos logit contributions
otion+0.023
 wasting+0.021
 grounded+0.020
 fighting+0.020
osing+0.020
Neg logit contributions
 flavor-0.017
boat-0.016
bye-0.016
 tal-0.016
iest-0.015
Token not
Token ID407
Feature activation-9.98e-03

Pos logit contributions
otion+0.080
osing+0.068
Acc+0.068
ains+0.065
 folders+0.064
Neg logit contributions
 flavor-0.053
 sound-0.048
 trick-0.048
imm-0.047
 his-0.047
Token happy
Token ID3772
Feature activation-2.15e-02

Pos logit contributions
otion+0.018
 wasting+0.016
 grounded+0.015
 fighting+0.015
osing+0.015
Neg logit contributions
 flavor-0.017
imm-0.016
boat-0.016
 tal-0.016
iest-0.015
Token.
Token ID13
Feature activation-3.38e-02

Pos logit contributions
otion+0.051
 wasting+0.047
 grounded+0.047
Acc+0.046
osing+0.046
Neg logit contributions
 flavor-0.023
imm-0.019
iest-0.019
bye-0.019
 flavour-0.019
Token She
Token ID1375
Feature activation-6.44e-02

Pos logit contributions
otion+0.050
 wasting+0.047
 grounded+0.046
 fighting+0.042
Acc+0.042
Neg logit contributions
 flavor-0.060
 His-0.060
 tal-0.059
bye-0.057
ww-0.057
Token says
Token ID1139
Feature activation-4.98e-02

Pos logit contributions
otion+0.143
Acc+0.128
nam+0.123
osing+0.119
ivated+0.119
Neg logit contributions
 tal-0.068
 trick-0.068
 carrot-0.067
oc-0.066
 fish-0.066
Token they
Token ID484
Feature activation-9.59e-02

Pos logit contributions
 wasting+0.128
otion+0.127
 grounded+0.126
Acc+0.123
assing+0.123
Neg logit contributions
 flavor-0.029
ww-0.026
 he-0.025
 tal-0.025
 His-0.024
Token have
Token ID423
Feature activation-1.37e-02

Pos logit contributions
otion+0.226
Acc+0.210
ivated+0.204
 salon+0.200
pering+0.197
Neg logit contributions
 flavor-0.084
ade-0.063
 flavour-0.061
 fish-0.061
 treat-0.059
Token to
Token ID284
Feature activation-2.03e-03

Pos logit contributions
otion+0.033
 wasting+0.030
 grounded+0.028
 fighting+0.028
osing+0.028
Neg logit contributions
 flavor-0.016
 tal-0.015
boat-0.014
bye-0.014
imm-0.014
Token stop
Token ID2245
Feature activation-5.73e-02

Pos logit contributions
otion+0.004
 wasting+0.004
 fighting+0.003
 grounded+0.003
 sewing+0.003
Neg logit contributions
 flavor-0.003
boat-0.003
 tal-0.003
imm-0.003
bye-0.003
Token fighting
Token ID4330
Feature activation-1.41e-02

Pos logit contributions
otion+0.091
 grounded+0.080
osing+0.079
Acc+0.075
 folders+0.073
Neg logit contributions
 Joe-0.091
 flavor-0.091
 his-0.089
orse-0.087
oy-0.087
Token and
Token ID290
Feature activation-1.31e-02

Pos logit contributions
otion+0.028
 wasting+0.027
 grounded+0.025
 fighting+0.024
 sewing+0.024
Neg logit contributions
 flavor-0.021
boat-0.019
bye-0.019
imm-0.019
 tal-0.019
Token not
Token ID407
Feature activation-1.40e-02

Pos logit contributions
otion+0.116
Acc+0.104
osing+0.103
ains+0.102
ems+0.102
Neg logit contributions
 sound-0.063
 his-0.061
 flavor-0.061
 trick-0.059
ggy-0.056
Token happy
Token ID3772
Feature activation-1.62e-02

Pos logit contributions
otion+0.027
 wasting+0.024
 grounded+0.023
osing+0.022
 fighting+0.022
Neg logit contributions
 flavor-0.022
boat-0.021
imm-0.021
 tal-0.021
iest-0.020
Token.
Token ID13
Feature activation-4.16e-02

Pos logit contributions
otion+0.037
 wasting+0.035
 grounded+0.034
Acc+0.033
osing+0.033
Neg logit contributions
 flavor-0.019
bye-0.016
imm-0.016
iest-0.016
boat-0.016
Token She
Token ID1375
Feature activation-6.06e-02

Pos logit contributions
otion+0.064
 wasting+0.061
 grounded+0.061
 fighting+0.056
Acc+0.056
Neg logit contributions
 His-0.070
 tal-0.070
 flavor-0.068
bye-0.065
ww-0.064
Token says
Token ID1139
Feature activation-5.12e-02

Pos logit contributions
otion+0.139
Acc+0.131
osing+0.120
nam+0.120
ivated+0.117
Neg logit contributions
 tal-0.059
 flavor-0.058
 trick-0.056
ww-0.056
 carrot-0.056
Token they
Token ID484
Feature activation-9.59e-02

Pos logit contributions
 grounded+0.139
 wasting+0.138
otion+0.138
Acc+0.134
assing+0.133
Neg logit contributions
 flavor-0.026
 he-0.021
ww-0.020
 tal-0.020
oy-0.019
Token have
Token ID423
Feature activation-1.10e-02

Pos logit contributions
otion+0.235
Acc+0.221
ivated+0.212
pering+0.206
 sewing+0.203
Neg logit contributions
 flavor-0.081
 flavour-0.055
 treat-0.054
oc-0.053
 fish-0.053
Token to
Token ID284
Feature activation-2.78e-03

Pos logit contributions
otion+0.025
 wasting+0.023
 fighting+0.022
 grounded+0.022
osing+0.022
Neg logit contributions
 flavor-0.014
 tal-0.013
boat-0.012
bye-0.012
imm-0.012
Token clean
Token ID3424
Feature activation-2.59e-02

Pos logit contributions
otion+0.005
 wasting+0.005
 fighting+0.005
 grounded+0.005
 sewing+0.005
Neg logit contributions
 flavor-0.004
boat-0.004
 tal-0.004
imm-0.004
bye-0.004
Token up
Token ID510
Feature activation-1.90e-02

Pos logit contributions
otion+0.049
 wasting+0.045
 grounded+0.043
osing+0.043
Acc+0.042
Neg logit contributions
 flavor-0.040
 tal-0.038
boat-0.037
imm-0.036
bye-0.035
Token and
Token ID290
Feature activation-4.42e-03

Pos logit contributions
otion+0.038
 wasting+0.034
 grounded+0.032
 fighting+0.032
osing+0.032
Neg logit contributions
 flavor-0.029
 tal-0.027
boat-0.027
bye-0.026
imm-0.026
Token But
Token ID887
Feature activation-2.81e-02

Pos logit contributions
otion+0.034
 wasting+0.033
 grounded+0.031
 fighting+0.031
 sewing+0.030
Neg logit contributions
 flavor-0.021
 tal-0.020
bye-0.019
boat-0.019
imm-0.019
Token she
Token ID673
Feature activation-6.77e-02

Pos logit contributions
otion+0.049
 wasting+0.044
 grounded+0.044
Acc+0.043
 sewing+0.043
Neg logit contributions
 flavor-0.046
bye-0.040
 flavour-0.040
ww-0.039
iest-0.039
Token sees
Token ID7224
Feature activation-1.11e-02

Pos logit contributions
otion+0.129
Acc+0.111
ivated+0.107
 wasting+0.104
Fighting+0.103
Neg logit contributions
 flavor-0.099
 carrot-0.096
 fish-0.092
 flavors-0.088
 rod-0.088
Token Sara
Token ID24799
Feature activation-7.39e-02

Pos logit contributions
otion+0.020
 wasting+0.019
 grounded+0.018
 fighting+0.018
 sewing+0.017
Neg logit contributions
 flavor-0.019
 tal-0.018
boat-0.018
imm-0.017
iest-0.017
Token and
Token ID290
Feature activation-2.03e-02

Pos logit contributions
Acc+0.162
otion+0.160
Girls+0.148
 narrative+0.148
 hey+0.145
Neg logit contributions
 flavor-0.075
boat-0.069
oc-0.064
 trick-0.062
 cone-0.061
Token Ben
Token ID3932
Feature activation-9.58e-02

Pos logit contributions
otion+0.035
 wasting+0.031
 grounded+0.031
osing+0.030
 fighting+0.029
Neg logit contributions
 flavor-0.036
 tal-0.034
 carrot-0.033
bye-0.032
boat-0.032
Token's
Token ID338
Feature activation-4.14e-02

Pos logit contributions
Acc+0.222
otion+0.216
Girls+0.206
 hey+0.202
issa+0.197
Neg logit contributions
 flavor-0.078
 dive-0.070
 his-0.069
boat-0.068
 place-0.064
Token faces
Token ID6698
Feature activation-5.17e-02

Pos logit contributions
otion+0.095
 wasting+0.086
 grounded+0.084
osing+0.084
Acc+0.080
Neg logit contributions
 flavor-0.055
 tal-0.049
boat-0.049
 flavour-0.046
iest-0.046
Token.
Token ID13
Feature activation+5.08e-04

Pos logit contributions
otion+0.131
 wasting+0.125
 grounded+0.123
Acc+0.123
 hey+0.122
Neg logit contributions
 flavor-0.040
boat-0.035
iest-0.035
imm-0.030
 flavour-0.029
Token They
Token ID1119
Feature activation-6.66e-02

Pos logit contributions
 flavor+0.001
boat+0.001
imm+0.001
 tal+0.001
bye+0.001
Neg logit contributions
otion-0.001
 wasting-0.001
 fighting-0.001
 grounded-0.001
 sewing-0.001
Token are
Token ID389
Feature activation-3.56e-02

Pos logit contributions
otion+0.142
Acc+0.136
 sewing+0.127
osing+0.125
Girls+0.120
Neg logit contributions
 flavor-0.081
 dive-0.077
 fish-0.076
 carrot-0.073
 wave-0.071
Token their
Token ID511
Feature activation-1.76e-02

Pos logit contributions
otion+0.001
 wasting+0.001
 fighting+0.001
 grounded+0.001
 sewing+0.001
Neg logit contributions
 flavor-0.000
boat-0.000
imm-0.000
 tal-0.000
bye-0.000
Token lesson
Token ID11483
Feature activation-1.92e-02

Pos logit contributions
otion+0.053
 wasting+0.049
 fighting+0.047
osing+0.047
 grounded+0.047
Neg logit contributions
 flavor-0.010
bye-0.009
 flavour-0.007
ww-0.007
iest-0.006
Token.
Token ID13
Feature activation-2.06e-02

Pos logit contributions
otion+0.046
 wasting+0.043
 fighting+0.040
 grounded+0.040
 sewing+0.040
Neg logit contributions
 flavor-0.021
bye-0.021
boat-0.020
iest-0.019
 tal-0.019
Token She
Token ID1375
Feature activation-4.76e-02

Pos logit contributions
otion+0.028
 wasting+0.026
 grounded+0.025
 fighting+0.024
 sewing+0.023
Neg logit contributions
 flavor-0.042
 tal-0.041
bye-0.040
ww-0.039
imm-0.038
Token says
Token ID1139
Feature activation-4.86e-02

Pos logit contributions
otion+0.114
 wasting+0.099
ivated+0.098
osing+0.096
oled+0.096
Neg logit contributions
 flavor-0.052
 carrot-0.049
 tal-0.047
bye-0.046
ww-0.044
Token they
Token ID484
Feature activation-9.54e-02

Pos logit contributions
 grounded+0.115
otion+0.113
assing+0.112
 wasting+0.108
osing+0.106
Neg logit contributions
 flavor-0.046
 he-0.041
orse-0.035
 flavour-0.034
 carrot-0.034
Token have
Token ID423
Feature activation-1.50e-02

Pos logit contributions
otion+0.235
ivated+0.216
pering+0.200
 backstage+0.199
Acc+0.197
Neg logit contributions
 flavor-0.087
bye-0.069
oc-0.067
 fish-0.066
 bait-0.063
Token to
Token ID284
Feature activation-9.81e-04

Pos logit contributions
otion+0.037
 wasting+0.034
 fighting+0.032
 grounded+0.032
osing+0.032
Neg logit contributions
 flavor-0.017
 tal-0.015
bye-0.015
boat-0.015
 flavour-0.014
Token stay
Token ID2652
Feature activation-2.20e-02

Pos logit contributions
otion+0.002
 wasting+0.002
 fighting+0.002
 grounded+0.002
 sewing+0.002
Neg logit contributions
 flavor-0.001
boat-0.001
imm-0.001
 tal-0.001
bye-0.001
Token in
Token ID287
Feature activation-2.37e-02

Pos logit contributions
otion+0.047
 wasting+0.041
osing+0.039
 fighting+0.038
Acc+0.037
Neg logit contributions
 flavor-0.031
imm-0.030
 tal-0.030
boat-0.030
bye-0.029
Token their
Token ID511
Feature activation-1.66e-02

Pos logit contributions
otion+0.048
osing+0.042
 wasting+0.042
 grounded+0.040
Acc+0.040
Neg logit contributions
 flavor-0.036
 tal-0.036
boat-0.033
bye-0.032
iest-0.031
Token not
Token ID407
Feature activation-1.07e-02

Pos logit contributions
otion+0.092
osing+0.082
Acc+0.079
ains+0.075
 wasting+0.074
Neg logit contributions
 flavor-0.061
 sound-0.059
 trick-0.056
 place-0.056
boat-0.055
Token happy
Token ID3772
Feature activation-9.06e-03

Pos logit contributions
otion+0.020
 wasting+0.018
 grounded+0.017
 fighting+0.017
osing+0.017
Neg logit contributions
 flavor-0.017
boat-0.017
 tal-0.016
imm-0.016
iest-0.016
Token.
Token ID13
Feature activation-3.25e-02

Pos logit contributions
otion+0.020
 wasting+0.019
 grounded+0.018
 fighting+0.018
osing+0.017
Neg logit contributions
 flavor-0.011
imm-0.010
boat-0.010
bye-0.010
 tal-0.010
Token She
Token ID1375
Feature activation-5.40e-02

Pos logit contributions
otion+0.051
 wasting+0.048
 grounded+0.047
 fighting+0.045
osing+0.044
Neg logit contributions
 flavor-0.056
 His-0.056
bye-0.055
 tal-0.054
ww-0.052
Token says
Token ID1139
Feature activation-4.86e-02

Pos logit contributions
otion+0.126
Acc+0.113
osing+0.109
ivated+0.108
 wasting+0.108
Neg logit contributions
 flavor-0.059
 carrot-0.056
 tal-0.054
 trick-0.052
oy-0.050
Token they
Token ID484
Feature activation-9.52e-02

Pos logit contributions
 grounded+0.119
otion+0.116
assing+0.113
 wasting+0.113
Acc+0.112
Neg logit contributions
 flavor-0.043
 he-0.036
 fish-0.036
 carrot-0.035
ww-0.033
Token have
Token ID423
Feature activation-8.40e-03

Pos logit contributions
otion+0.235
Acc+0.222
ivated+0.219
osing+0.200
pering+0.199
Neg logit contributions
 flavor-0.091
 flavour-0.064
 fish-0.063
 bait-0.063
oc-0.061
Token to
Token ID284
Feature activation-7.43e-04

Pos logit contributions
otion+0.019
 wasting+0.018
 fighting+0.017
 grounded+0.017
osing+0.017
Neg logit contributions
 flavor-0.010
 tal-0.010
boat-0.010
bye-0.009
imm-0.009
Token hurry
Token ID23290
Feature activation-6.57e-03

Pos logit contributions
otion+0.001
 wasting+0.001
 fighting+0.001
 grounded+0.001
 sewing+0.001
Neg logit contributions
 flavor-0.001
boat-0.001
imm-0.001
 tal-0.001
bye-0.001
Token.
Token ID13
Feature activation-3.25e-02

Pos logit contributions
otion+0.013
 wasting+0.012
 fighting+0.012
 grounded+0.011
 sewing+0.011
Neg logit contributions
 flavor-0.010
boat-0.010
imm-0.009
 tal-0.009
bye-0.009
Token She
Token ID1375
Feature activation-5.12e-02

Pos logit contributions
otion+0.052
 wasting+0.048
 grounded+0.045
 fighting+0.044
osing+0.043
Neg logit contributions
 His-0.057
 flavor-0.055
 tal-0.055
bye-0.054
ww-0.052
Token forgive
Token ID20927
Feature activation-3.15e-03

Pos logit contributions
otion+0.003
 wasting+0.003
 fighting+0.003
 grounded+0.003
 sewing+0.003
Neg logit contributions
 flavor-0.003
boat-0.003
imm-0.003
 tal-0.003
bye-0.003
Token them
Token ID606
Feature activation-3.80e-02

Pos logit contributions
otion+0.004
 wasting+0.003
 fighting+0.003
 grounded+0.003
 sewing+0.003
Neg logit contributions
 flavor-0.007
boat-0.007
imm-0.007
 tal-0.007
bye-0.007
Token.
Token ID13
Feature activation-2.95e-02

Pos logit contributions
otion+0.099
 wasting+0.091
 sewing+0.091
 grounded+0.088
osing+0.087
Neg logit contributions
 flavor-0.032
bye-0.028
 flavour-0.024
 His-0.022
iest-0.022
Token She
Token ID1375
Feature activation-4.86e-02

Pos logit contributions
otion+0.044
 wasting+0.039
 grounded+0.039
 fighting+0.037
 sewing+0.037
Neg logit contributions
 flavor-0.058
 tal-0.055
bye-0.054
 His-0.052
ww-0.052
Token says
Token ID1139
Feature activation-5.00e-02

Pos logit contributions
otion+0.115
 wasting+0.098
osing+0.097
ivated+0.097
Acc+0.094
Neg logit contributions
 flavor-0.056
 carrot-0.053
 tal-0.050
bye-0.047
 cone-0.047
Token they
Token ID484
Feature activation-9.45e-02

Pos logit contributions
 grounded+0.120
otion+0.117
assing+0.116
 wasting+0.112
osing+0.110
Neg logit contributions
 flavor-0.047
 he-0.041
 carrot-0.034
 fish-0.034
ww-0.034
Token have
Token ID423
Feature activation-1.18e-02

Pos logit contributions
otion+0.235
ivated+0.214
pering+0.203
 backstage+0.200
 sewing+0.197
Neg logit contributions
 flavor-0.085
 fish-0.063
oc-0.062
bye-0.061
 treat-0.061
Token to
Token ID284
Feature activation-4.36e-03

Pos logit contributions
otion+0.028
 wasting+0.026
 fighting+0.025
 grounded+0.024
osing+0.024
Neg logit contributions
 flavor-0.014
 tal-0.013
bye-0.013
boat-0.012
imm-0.012
Token learn
Token ID2193
Feature activation-3.31e-04

Pos logit contributions
otion+0.009
 wasting+0.009
 fighting+0.008
 grounded+0.008
 sewing+0.008
Neg logit contributions
 flavor-0.006
boat-0.006
 tal-0.006
imm-0.006
bye-0.006
Token their
Token ID511
Feature activation-1.76e-02

Pos logit contributions
otion+0.001
 wasting+0.001
 fighting+0.001
 grounded+0.001
 sewing+0.001
Neg logit contributions
 flavor-0.000
boat-0.000
imm-0.000
 tal-0.000
bye-0.000
Token lesson
Token ID11483
Feature activation-1.92e-02

Pos logit contributions
otion+0.053
 wasting+0.049
 fighting+0.047
osing+0.047
 grounded+0.047
Neg logit contributions
 flavor-0.010
bye-0.009
 flavour-0.007
ww-0.007
iest-0.006
Token and
Token ID290
Feature activation+4.48e-04

Pos logit contributions
otion+0.070
 wasting+0.068
 grounded+0.063
 sewing+0.062
osing+0.062
Neg logit contributions
 flavor-0.034
boat-0.034
bye-0.033
iest-0.031
imm-0.030
Token kind
Token ID1611
Feature activation-1.04e-03

Pos logit contributions
 flavor+0.001
boat+0.001
imm+0.001
 tal+0.001
bye+0.001
Neg logit contributions
otion-0.001
 wasting-0.001
 fighting-0.001
 grounded-0.001
 sewing-0.001
Token.
Token ID13
Feature activation-1.21e-02

Pos logit contributions
otion+0.002
 wasting+0.002
 fighting+0.002
 grounded+0.002
 sewing+0.002
Neg logit contributions
 flavor-0.001
boat-0.001
imm-0.001
 tal-0.001
bye-0.001
Token She
Token ID1375
Feature activation-5.17e-02

Pos logit contributions
otion+0.019
 wasting+0.018
 fighting+0.017
 grounded+0.016
osing+0.016
Neg logit contributions
 flavor-0.023
bye-0.022
 tal-0.022
boat-0.022
imm-0.021
Token says
Token ID1139
Feature activation-5.24e-02

Pos logit contributions
otion+0.114
ivated+0.096
 wasting+0.095
osing+0.094
oled+0.093
Neg logit contributions
 flavor-0.068
 carrot-0.066
 tal-0.063
bye-0.062
 fish-0.059
Token they
Token ID484
Feature activation-9.43e-02

Pos logit contributions
assing+0.126
otion+0.123
 grounded+0.123
 wasting+0.120
osing+0.116
Neg logit contributions
 flavor-0.045
 he-0.043
bye-0.038
 fish-0.037
 carrot-0.036
Token have
Token ID423
Feature activation-5.04e-03

Pos logit contributions
otion+0.230
ivated+0.206
pering+0.204
 backstage+0.198
 occurring+0.191
Neg logit contributions
 flavor-0.089
bye-0.071
oc-0.069
 fish-0.066
 flavour-0.066
Token to
Token ID284
Feature activation+5.03e-03

Pos logit contributions
otion+0.011
 wasting+0.010
 fighting+0.010
 grounded+0.010
osing+0.010
Neg logit contributions
 flavor-0.006
 tal-0.006
boat-0.006
imm-0.006
bye-0.006
Token wait
Token ID4043
Feature activation-2.88e-02

Pos logit contributions
 flavor+0.007
imm+0.007
boat+0.007
 tal+0.007
iest+0.007
Neg logit contributions
otion-0.010
 wasting-0.009
 fighting-0.009
 grounded-0.009
 sewing-0.008
Token until
Token ID1566
Feature activation-2.04e-02

Pos logit contributions
otion+0.060
 wasting+0.055
 grounded+0.052
 fighting+0.052
osing+0.050
Neg logit contributions
 flavor-0.039
bye-0.036
imm-0.036
iest-0.036
boat-0.035
Token they
Token ID484
Feature activation-5.28e-02

Pos logit contributions
otion+0.040
 wasting+0.036
 grounded+0.034
osing+0.034
 fighting+0.034
Neg logit contributions
 flavor-0.031
bye-0.029
boat-0.029
 tal-0.027
 flavour-0.027
Token and
Token ID290
Feature activation-6.70e-02

Pos logit contributions
otion+0.079
 wasting+0.075
 grounded+0.073
assing+0.071
osing+0.071
Neg logit contributions
 flavor-0.037
iest-0.032
bye-0.031
 flavour-0.030
 he-0.030
Token angry
Token ID7954
Feature activation-3.56e-02

Pos logit contributions
otion+0.110
 folders+0.100
osing+0.099
 sewing+0.097
ptions+0.095
Neg logit contributions
 sound-0.101
 he-0.095
 his-0.091
bye-0.089
 His-0.085
Token.
Token ID13
Feature activation-4.32e-02

Pos logit contributions
otion+0.093
 wasting+0.089
 grounded+0.088
Acc+0.087
 sewing+0.086
Neg logit contributions
bye-0.025
 flavor-0.023
iest-0.019
oy-0.019
boat-0.018
Token She
Token ID1375
Feature activation-6.33e-02

Pos logit contributions
otion+0.078
 wasting+0.071
 grounded+0.069
osing+0.066
 salon+0.065
Neg logit contributions
 His-0.068
 tal-0.062
 flavor-0.061
ww-0.060
bye-0.060
Token says
Token ID1139
Feature activation-5.11e-02

Pos logit contributions
otion+0.144
Acc+0.128
osing+0.123
nam+0.121
 sewing+0.120
Neg logit contributions
ww-0.063
 tal-0.063
 carrot-0.060
 trick-0.058
oc-0.058
Token they
Token ID484
Feature activation-9.41e-02

Pos logit contributions
 wasting+0.137
otion+0.137
 grounded+0.134
Acc+0.131
assing+0.131
Neg logit contributions
 flavor-0.024
ww-0.024
 tal-0.021
 he-0.021
 His-0.018
Token are
Token ID389
Feature activation-4.81e-02

Pos logit contributions
otion+0.224
ivated+0.211
Acc+0.203
 salon+0.200
 backstage+0.199
Neg logit contributions
 flavor-0.081
oc-0.064
o-0.060
 fish-0.060
cream-0.060
Token naughty
Token ID45128
Feature activation-5.04e-02

Pos logit contributions
otion+0.084
 salon+0.071
osing+0.068
Acc+0.067
oled+0.065
Neg logit contributions
 carrot-0.071
 flavor-0.071
 fish-0.069
 bait-0.068
 his-0.068
Token and
Token ID290
Feature activation-4.05e-02

Pos logit contributions
otion+0.116
 wasting+0.107
osing+0.106
Acc+0.106
assing+0.104
Neg logit contributions
bye-0.053
 flavor-0.053
est-0.051
iest-0.050
 buddy-0.046
Token silly
Token ID14397
Feature activation-3.83e-02

Pos logit contributions
otion+0.072
osing+0.057
 sewing+0.056
 wasting+0.056
assing+0.055
Neg logit contributions
 flavor-0.065
bye-0.065
ww-0.064
boat-0.061
 tal-0.059
Token.
Token ID13
Feature activation-2.52e-02

Pos logit contributions
otion+0.092
 wasting+0.086
Acc+0.086
osing+0.086
 grounded+0.084
Neg logit contributions
 flavor-0.036
iest-0.034
bye-0.034
est-0.032
boat-0.029
Token They
Token ID1119
Feature activation-1.73e-02

Pos logit contributions
 flavor+0.001
boat+0.001
imm+0.001
 tal+0.001
bye+0.001
Neg logit contributions
otion-0.001
 wasting-0.001
 fighting-0.001
 grounded-0.001
 sewing-0.001
Token wanted
Token ID2227
Feature activation+1.46e-02

Pos logit contributions
otion+0.036
 wasting+0.033
 grounded+0.031
 fighting+0.031
 sewing+0.031
Neg logit contributions
 flavor-0.025
boat-0.024
bye-0.023
 tal-0.023
imm-0.022
Token to
Token ID284
Feature activation+3.82e-02

Pos logit contributions
imm+0.025
boat+0.024
 tal+0.023
bye+0.023
ww+0.022
Neg logit contributions
 wasting-0.027
otion-0.026
 fighting-0.025
 sewing-0.024
 grounded-0.023
Token eat
Token ID4483
Feature activation+2.25e-02

Pos logit contributions
imm+0.080
boat+0.076
 tal+0.075
ww+0.074
iest+0.073
Neg logit contributions
 wasting-0.056
otion-0.054
 fighting-0.052
 sewing-0.047
 grounded-0.045
Token something
Token ID1223
Feature activation+7.06e-02

Pos logit contributions
boat+0.040
imm+0.040
bye+0.039
 tal+0.038
ww+0.037
Neg logit contributions
 wasting-0.039
otion-0.038
 fighting-0.037
 sewing-0.034
 grounded-0.032
Token y
Token ID331
Feature activation+6.68e-02

Pos logit contributions
 tal+0.157
boat+0.153
bye+0.150
imm+0.140
ah+0.140
Neg logit contributions
 wasting-0.104
 fighting-0.098
otion-0.089
 sewing-0.082
 crying-0.078
Tokenummy
Token ID13513
Feature activation+4.33e-02

Pos logit contributions
 tal+0.143
boat+0.141
Ar+0.133
orse+0.133
oc+0.126
Neg logit contributions
otion-0.086
 fighting-0.076
 wasting-0.075
els-0.062
osing-0.058
Token.
Token ID13
Feature activation+9.37e-03

Pos logit contributions
boat+0.083
imm+0.082
 tal+0.081
bye+0.079
ww+0.075
Neg logit contributions
 wasting-0.063
otion-0.063
 fighting-0.061
 sewing-0.054
 grounded-0.052
Token Mom
Token ID11254
Feature activation-4.01e-03

Pos logit contributions
boat+0.016
imm+0.016
 flavor+0.015
 tal+0.015
iest+0.015
Neg logit contributions
otion-0.017
 wasting-0.016
 fighting-0.016
 grounded-0.015
 sewing-0.014
Token said
Token ID531
Feature activation-1.57e-02

Pos logit contributions
otion+0.008
 wasting+0.008
 fighting+0.007
 grounded+0.007
 sewing+0.007
Neg logit contributions
 flavor-0.006
boat-0.005
imm-0.005
 tal-0.005
bye-0.005
Token she
Token ID673
Feature activation-1.25e-02

Pos logit contributions
otion+0.035
 wasting+0.034
 grounded+0.033
 fighting+0.032
 sewing+0.031
Neg logit contributions
 flavor-0.020
 tal-0.017
iest-0.017
 flavour-0.017
boat-0.017
Token,
Token ID11
Feature activation+1.35e-03

Pos logit contributions
boat+0.035
imm+0.033
bye+0.033
 tal+0.033
 flavor+0.032
Neg logit contributions
otion-0.040
 wasting-0.039
 fighting-0.037
 grounded-0.036
osing-0.034
Token forty
Token ID16571
Feature activation+6.55e-02

Pos logit contributions
 flavor+0.002
boat+0.002
imm+0.002
 tal+0.002
bye+0.002
Neg logit contributions
otion-0.002
 wasting-0.002
 fighting-0.002
 grounded-0.002
 sewing-0.002
Token-
Token ID12
Feature activation+3.13e-02

Pos logit contributions
boat+0.095
 tal+0.088
imm+0.085
bye+0.079
 fins+0.077
Neg logit contributions
otion-0.118
 wasting-0.117
 fighting-0.113
 grounded-0.106
osing-0.106
Tokenfive
Token ID13261
Feature activation+2.46e-02

Pos logit contributions
 tal+0.053
imm+0.051
boat+0.051
 flavor+0.051
 carrot+0.047
Neg logit contributions
otion-0.054
 wasting-0.050
 grounded-0.048
osing-0.047
 fighting-0.047
Token,
Token ID11
Feature activation-9.00e-03

Pos logit contributions
boat+0.039
 tal+0.039
imm+0.038
 flavor+0.037
bye+0.036
Neg logit contributions
otion-0.045
 wasting-0.043
 fighting-0.042
 grounded-0.039
 sewing-0.038
Token forty
Token ID16571
Feature activation+6.27e-02

Pos logit contributions
otion+0.016
 wasting+0.015
 fighting+0.014
 grounded+0.014
 sewing+0.013
Neg logit contributions
 flavor-0.015
 tal-0.015
boat-0.015
imm-0.014
bye-0.014
Token-
Token ID12
Feature activation+2.99e-02

Pos logit contributions
boat+0.090
 tal+0.082
imm+0.079
bye+0.076
ull+0.072
Neg logit contributions
 wasting-0.115
otion-0.113
 fighting-0.112
 salon-0.104
 sewing-0.104
Tokensix
Token ID19412
Feature activation+2.66e-02

Pos logit contributions
 tal+0.053
boat+0.052
imm+0.052
 flavor+0.051
 carrot+0.047
Neg logit contributions
otion-0.048
 wasting-0.045
 grounded-0.043
 fighting-0.043
osing-0.042
Token,
Token ID11
Feature activation-2.78e-02

Pos logit contributions
boat+0.040
imm+0.040
 tal+0.038
 flavor+0.038
bye+0.037
Neg logit contributions
otion-0.049
 wasting-0.048
 fighting-0.047
 sewing-0.044
 grounded-0.043
Token forty
Token ID16571
Feature activation+6.47e-02

Pos logit contributions
otion+0.054
 wasting+0.048
 grounded+0.047
 fighting+0.046
Acc+0.044
Neg logit contributions
 flavor-0.044
boat-0.041
 tal-0.040
ww-0.039
 flavour-0.039
Token-
Token ID12
Feature activation+2.95e-02

Pos logit contributions
boat+0.094
 tal+0.084
imm+0.080
bye+0.079
ull+0.075
Neg logit contributions
 wasting-0.117
otion-0.115
 fighting-0.114
els-0.107
 salon-0.107
Token had
Token ID550
Feature activation+2.85e-02

Pos logit contributions
imm+0.045
boat+0.045
iest+0.044
 flavor+0.044
bye+0.042
Neg logit contributions
 wasting-0.038
otion-0.036
 fighting-0.035
 grounded-0.035
 sewing-0.034
Token a
Token ID257
Feature activation+2.87e-02

Pos logit contributions
imm+0.055
boat+0.054
iest+0.053
oc+0.052
bye+0.052
Neg logit contributions
 wasting-0.042
 fighting-0.039
 grounded-0.039
otion-0.038
 sewing-0.037
Token bird
Token ID6512
Feature activation+9.35e-03

Pos logit contributions
imm+0.046
boat+0.042
iest+0.042
bye+0.041
 tal+0.040
Neg logit contributions
 wasting-0.052
 fighting-0.051
 sewing-0.050
otion-0.050
 grounded-0.049
Token's
Token ID338
Feature activation+1.87e-02

Pos logit contributions
 flavor+0.016
imm+0.015
boat+0.015
 tal+0.015
bye+0.015
Neg logit contributions
otion-0.016
 wasting-0.015
 fighting-0.015
 grounded-0.014
 sewing-0.014
Token eye
Token ID4151
Feature activation+1.18e-02

Pos logit contributions
imm+0.027
boat+0.027
 flavor+0.026
 tal+0.026
ww+0.025
Neg logit contributions
otion-0.035
 wasting-0.034
 sewing-0.033
 fighting-0.033
 grounded-0.031
Token view
Token ID1570
Feature activation+6.68e-02

Pos logit contributions
 flavor+0.019
imm+0.019
 tal+0.019
boat+0.018
bye+0.018
Neg logit contributions
otion-0.021
 wasting-0.020
 fighting-0.019
 sewing-0.019
 grounded-0.019
Token of
Token ID286
Feature activation+2.20e-02

Pos logit contributions
 tal+0.141
orse+0.129
oc+0.129
ww+0.128
oy+0.123
Neg logit contributions
otion-0.083
 fighting-0.080
 wasting-0.077
 grounded-0.065
 sewing-0.065
Token the
Token ID262
Feature activation-2.05e-02

Pos logit contributions
imm+0.041
boat+0.039
ww+0.039
bye+0.039
 flavor+0.038
Neg logit contributions
 wasting-0.034
otion-0.034
 fighting-0.033
 sewing-0.030
 grounded-0.029
Token whole
Token ID2187
Feature activation+1.83e-02

Pos logit contributions
otion+0.051
 wasting+0.047
 fighting+0.045
 grounded+0.045
osing+0.044
Neg logit contributions
 flavor-0.023
bye-0.022
 tal-0.021
boat-0.021
 carrot-0.020
Token world
Token ID995
Feature activation+2.65e-02

Pos logit contributions
imm+0.029
boat+0.029
 tal+0.028
 flavor+0.028
iest+0.027
Neg logit contributions
otion-0.032
 wasting-0.031
 fighting-0.031
 sewing-0.029
 grounded-0.029
Token.
Token ID13
Feature activation+2.44e-02

Pos logit contributions
 tal+0.043
 flavor+0.043
imm+0.041
boat+0.040
ww+0.040
Neg logit contributions
otion-0.047
 wasting-0.044
 fighting-0.044
 grounded-0.041
 sewing-0.040
Token
Token ID198
Feature activation+2.54e-03

Pos logit contributions
 flavor+0.011
boat+0.011
imm+0.011
 tal+0.011
iest+0.011
Neg logit contributions
otion-0.014
 wasting-0.013
 fighting-0.013
 grounded-0.012
 sewing-0.012
Token
Token ID198
Feature activation-1.14e-02

Pos logit contributions
 flavor+0.004
boat+0.004
imm+0.004
 tal+0.004
bye+0.004
Neg logit contributions
otion-0.005
 wasting-0.005
 fighting-0.005
 grounded-0.004
 sewing-0.004
TokenTim
Token ID14967
Feature activation+5.63e-03

Pos logit contributions
otion+0.024
 wasting+0.023
 fighting+0.021
 grounded+0.021
 sewing+0.020
Neg logit contributions
boat-0.016
 flavor-0.016
imm-0.015
 tal-0.015
bye-0.015
Tokenmy
Token ID1820
Feature activation+2.11e-02

Pos logit contributions
 flavor+0.013
boat+0.013
 tal+0.013
imm+0.013
bye+0.013
Neg logit contributions
otion-0.006
 wasting-0.005
 fighting-0.005
 grounded-0.005
 sewing-0.004
Token smiled
Token ID13541
Feature activation+1.60e-02

Pos logit contributions
boat+0.036
iest+0.035
 flavor+0.035
 tal+0.035
imm+0.034
Neg logit contributions
otion-0.035
 wasting-0.034
 fighting-0.033
 grounded-0.032
 sewing-0.032
Token and
Token ID290
Feature activation+6.54e-02

Pos logit contributions
 flavor+0.033
boat+0.032
imm+0.032
ww+0.032
 tal+0.032
Neg logit contributions
otion-0.021
 wasting-0.020
 fighting-0.019
 grounded-0.018
 sewing-0.018
Token nodded
Token ID14464
Feature activation+1.86e-02

Pos logit contributions
iest+0.148
boat+0.139
imm+0.137
 flavor+0.136
umm+0.135
Neg logit contributions
 wasting-0.073
 fighting-0.072
 crying-0.067
 grounded-0.067
 sewing-0.066
Token his
Token ID465
Feature activation+3.14e-02

Pos logit contributions
 flavor+0.030
ww+0.030
 tal+0.029
boat+0.029
imm+0.029
Neg logit contributions
otion-0.033
 fighting-0.032
 wasting-0.031
 sewing-0.030
 grounded-0.029
Token head
Token ID1182
Feature activation+2.48e-02

Pos logit contributions
boat+0.074
iest+0.074
imm+0.071
 flavor+0.070
cream+0.065
Neg logit contributions
 fighting-0.031
 wasting-0.031
 sewing-0.030
 grounded-0.030
 weeping-0.028
Token.
Token ID13
Feature activation+1.11e-02

Pos logit contributions
 flavor+0.041
 tal+0.041
ww+0.041
imm+0.040
boat+0.039
Neg logit contributions
otion-0.043
 fighting-0.040
 wasting-0.040
 sewing-0.038
 grounded-0.037
Token He
Token ID679
Feature activation+2.88e-02

Pos logit contributions
 flavor+0.019
boat+0.018
 tal+0.018
imm+0.018
iest+0.018
Neg logit contributions
otion-0.020
 wasting-0.019
 fighting-0.018
 grounded-0.017
 sewing-0.017
Token.
Token ID13
Feature activation+2.31e-02

Pos logit contributions
 flavor+0.009
 tal+0.009
imm+0.009
boat+0.009
bye+0.008
Neg logit contributions
otion-0.012
 wasting-0.011
 fighting-0.011
 grounded-0.010
 sewing-0.010
Token Jack
Token ID3619
Feature activation-1.98e-03

Pos logit contributions
 tal+0.036
imm+0.034
boat+0.034
iest+0.034
 flavor+0.033
Neg logit contributions
otion-0.044
 fighting-0.042
 wasting-0.042
osing-0.037
Acc-0.037
Token had
Token ID550
Feature activation+1.59e-02

Pos logit contributions
otion+0.003
 wasting+0.003
 fighting+0.003
 grounded+0.003
 sewing+0.003
Neg logit contributions
 flavor-0.003
boat-0.003
imm-0.003
 tal-0.003
bye-0.003
Token a
Token ID257
Feature activation+2.39e-02

Pos logit contributions
imm+0.031
boat+0.031
 tal+0.030
iest+0.029
bye+0.029
Neg logit contributions
 wasting-0.024
otion-0.023
 fighting-0.023
 sewing-0.022
 grounded-0.021
Token guitar
Token ID10047
Feature activation+1.62e-02

Pos logit contributions
imm+0.037
boat+0.036
iest+0.035
 tal+0.035
bye+0.035
Neg logit contributions
 wasting-0.044
 sewing-0.044
 fighting-0.043
otion-0.043
 grounded-0.040
Token that
Token ID326
Feature activation+7.08e-02

Pos logit contributions
 tal+0.030
 flavor+0.029
imm+0.029
boat+0.028
ww+0.028
Neg logit contributions
otion-0.026
 wasting-0.024
 fighting-0.024
 sewing-0.023
 grounded-0.023
Token he
Token ID339
Feature activation+1.80e-02

Pos logit contributions
 tal+0.123
imm+0.105
oy+0.102
eed+0.102
oc+0.098
Neg logit contributions
 sewing-0.116
otion-0.113
 fighting-0.112
 wasting-0.112
 crying-0.112
Token loved
Token ID6151
Feature activation+2.51e-02

Pos logit contributions
 tal+0.037
 flavor+0.035
imm+0.035
boat+0.035
bye+0.034
Neg logit contributions
otion-0.024
 wasting-0.024
 fighting-0.023
 grounded-0.022
 sewing-0.022
Token to
Token ID284
Feature activation+2.27e-02

Pos logit contributions
imm+0.044
 tal+0.043
boat+0.041
iest+0.040
 flavor+0.040
Neg logit contributions
 fighting-0.042
 wasting-0.042
otion-0.041
 sewing-0.040
 grounded-0.037
Token play
Token ID711
Feature activation+9.30e-03

Pos logit contributions
 tal+0.039
imm+0.039
 flavor+0.037
boat+0.037
ww+0.036
Neg logit contributions
otion-0.039
 wasting-0.036
 fighting-0.035
 sewing-0.034
 grounded-0.033
Token.
Token ID13
Feature activation+2.96e-02

Pos logit contributions
 tal+0.014
 flavor+0.014
imm+0.014
boat+0.014
bye+0.013
Neg logit contributions
otion-0.018
 wasting-0.017
 fighting-0.016
 grounded-0.016
 sewing-0.016
Token.
Token ID13
Feature activation+1.64e-02

Pos logit contributions
imm+0.024
 tal+0.024
 flavor+0.024
boat+0.023
ww+0.023
Neg logit contributions
otion-0.024
 wasting-0.023
 fighting-0.022
 grounded-0.021
 sewing-0.021
Token They
Token ID1119
Feature activation-2.72e-02

Pos logit contributions
imm+0.030
boat+0.030
 flavor+0.030
iest+0.030
 tal+0.029
Neg logit contributions
otion-0.027
 wasting-0.025
 fighting-0.024
 sewing-0.023
 grounded-0.023
Token pet
Token ID4273
Feature activation+6.72e-03

Pos logit contributions
otion+0.056
 wasting+0.050
 fighting+0.048
 grounded+0.047
osing+0.047
Neg logit contributions
 flavor-0.041
boat-0.039
 tal-0.038
 carrot-0.038
bye-0.037
Token his
Token ID465
Feature activation+2.43e-02

Pos logit contributions
imm+0.012
 flavor+0.012
boat+0.012
 tal+0.012
bye+0.011
Neg logit contributions
otion-0.011
 wasting-0.010
 fighting-0.010
 grounded-0.010
 sewing-0.009
Token nose
Token ID9686
Feature activation+8.94e-04

Pos logit contributions
imm+0.040
boat+0.038
iest+0.036
ww+0.035
bye+0.035
Neg logit contributions
 wasting-0.042
 fighting-0.041
otion-0.041
 sewing-0.040
 grounded-0.038
Token and
Token ID290
Feature activation+2.19e-02

Pos logit contributions
 flavor+0.002
boat+0.002
imm+0.002
 tal+0.002
bye+0.002
Neg logit contributions
otion-0.001
 wasting-0.001
 fighting-0.001
 grounded-0.001
 sewing-0.001
Token his
Token ID465
Feature activation+3.59e-02

Pos logit contributions
imm+0.037
boat+0.035
iest+0.035
bye+0.034
 flavor+0.033
Neg logit contributions
 wasting-0.039
otion-0.038
 fighting-0.037
 sewing-0.035
 grounded-0.035
Token man
Token ID582
Feature activation-1.02e-02

Pos logit contributions
imm+0.057
boat+0.054
iest+0.052
ww+0.051
bye+0.049
Neg logit contributions
 fighting-0.063
 wasting-0.063
 sewing-0.061
otion-0.060
 crying-0.057
Tokene
Token ID68
Feature activation+7.15e-03

Pos logit contributions
otion+0.021
 wasting+0.020
 grounded+0.019
 fighting+0.019
 sewing+0.018
Neg logit contributions
 flavor-0.014
 tal-0.014
boat-0.014
imm-0.013
bye-0.013
Token and
Token ID290
Feature activation+3.37e-02

Pos logit contributions
boat+0.011
 flavor+0.011
imm+0.011
 tal+0.011
bye+0.011
Neg logit contributions
otion-0.013
 wasting-0.013
 fighting-0.012
 grounded-0.012
 sewing-0.011
Token his
Token ID465
Feature activation+3.28e-02

Pos logit contributions
imm+0.060
iest+0.057
boat+0.055
bye+0.052
 flavor+0.052
Neg logit contributions
 wasting-0.059
 fighting-0.055
otion-0.055
 sewing-0.052
 grounded-0.052
Token.
Token ID13
Feature activation+8.55e-03

Pos logit contributions
 flavor+0.006
boat+0.006
imm+0.006
 tal+0.006
bye+0.005
Neg logit contributions
otion-0.009
 wasting-0.008
 fighting-0.008
 grounded-0.008
 sewing-0.007
Token
Token ID198
Feature activation+6.60e-03

Pos logit contributions
 flavor+0.014
boat+0.014
imm+0.014
 tal+0.014
iest+0.014
Neg logit contributions
otion-0.015
 wasting-0.014
 fighting-0.014
 grounded-0.013
 sewing-0.013
Token
Token ID198
Feature activation-1.58e-02

Pos logit contributions
 flavor+0.010
boat+0.010
imm+0.010
 tal+0.010
bye+0.009
Neg logit contributions
otion-0.013
 wasting-0.012
 fighting-0.012
 grounded-0.011
 sewing-0.011
TokenThe
Token ID464
Feature activation-1.70e-02

Pos logit contributions
otion+0.034
 wasting+0.031
 fighting+0.030
 grounded+0.029
 sewing+0.028
Neg logit contributions
boat-0.022
 flavor-0.021
ww-0.021
bye-0.021
 tal-0.021
Token little
Token ID1310
Feature activation-7.90e-03

Pos logit contributions
otion+0.037
 wasting+0.033
 grounded+0.032
 fighting+0.031
osing+0.031
Neg logit contributions
 flavor-0.025
bye-0.022
boat-0.022
iest-0.022
 flavour-0.022
Token girl
Token ID2576
Feature activation+1.16e-02

Pos logit contributions
otion+0.014
 wasting+0.013
 grounded+0.013
 fighting+0.013
osing+0.012
Neg logit contributions
 flavor-0.013
boat-0.013
 tal-0.013
imm-0.013
bye-0.013
Token couldn
Token ID3521
Feature activation-4.93e-03

Pos logit contributions
 flavor+0.018
imm+0.017
boat+0.017
 tal+0.017
iest+0.017
Neg logit contributions
otion-0.022
 wasting-0.021
 fighting-0.021
 grounded-0.020
 sewing-0.019
Token't
Token ID470
Feature activation+2.64e-02

Pos logit contributions
otion+0.006
 wasting+0.005
 fighting+0.005
 grounded+0.005
 sewing+0.004
Neg logit contributions
 flavor-0.011
boat-0.011
 tal-0.011
imm-0.011
bye-0.011
Token believe
Token ID1975
Feature activation-3.07e-02

Pos logit contributions
imm+0.045
 tal+0.044
ww+0.044
 flavor+0.044
boat+0.042
Neg logit contributions
otion-0.046
 fighting-0.044
 wasting-0.043
 grounded-0.041
 hey-0.040
Token what
Token ID644
Feature activation+2.62e-03

Pos logit contributions
otion+0.057
 grounded+0.054
 wasting+0.054
 sewing+0.050
 fighting+0.049
Neg logit contributions
 flavor-0.043
imm-0.042
boat-0.042
iest-0.041
 tal-0.041
Token she
Token ID673
Feature activation+7.31e-03

Pos logit contributions
imm+0.005
 flavor+0.005
boat+0.005
 tal+0.005
bye+0.004
Neg logit contributions
otion-0.004
 wasting-0.004
 fighting-0.004
 grounded-0.004
 sewing-0.004
Token Grand
Token ID5675
Feature activation-1.58e-02

Pos logit contributions
 flavor+0.006
boat+0.006
imm+0.006
 tal+0.006
bye+0.006
Neg logit contributions
otion-0.008
 wasting-0.008
 fighting-0.007
 grounded-0.007
 sewing-0.007
Tokenma
Token ID2611
Feature activation+2.16e-02

Pos logit contributions
otion+0.022
 wasting+0.021
 fighting+0.019
 grounded+0.019
 sewing+0.019
Neg logit contributions
 flavor-0.033
imm-0.031
bye-0.031
boat-0.031
iest-0.031
Token hugged
Token ID41130
Feature activation-2.02e-02

Pos logit contributions
boat+0.035
 tal+0.035
 flavor+0.035
imm+0.034
bye+0.033
Neg logit contributions
otion-0.037
 wasting-0.036
 fighting-0.035
 grounded-0.034
 sewing-0.033
Token them
Token ID606
Feature activation+1.58e-02

Pos logit contributions
otion+0.030
 wasting+0.028
 grounded+0.025
 fighting+0.025
osing+0.024
Neg logit contributions
 flavor-0.041
bye-0.040
boat-0.039
 tal-0.039
imm-0.039
Token and
Token ID290
Feature activation+4.96e-02

Pos logit contributions
 tal+0.029
 flavor+0.029
imm+0.028
boat+0.028
iest+0.027
Neg logit contributions
otion-0.025
 wasting-0.024
 fighting-0.023
 grounded-0.022
 sewing-0.021
Token said
Token ID531
Feature activation+5.85e-03

Pos logit contributions
imm+0.091
boat+0.088
 tal+0.085
iest+0.083
bye+0.082
Neg logit contributions
 wasting-0.078
otion-0.073
 fighting-0.072
 grounded-0.069
 sewing-0.067
Token,
Token ID11
Feature activation-4.72e-03

Pos logit contributions
 flavor+0.008
boat+0.008
imm+0.008
 tal+0.008
bye+0.008
Neg logit contributions
otion-0.012
 wasting-0.011
 fighting-0.011
 grounded-0.011
 sewing-0.010
Token �
Token ID6184
Feature activation-9.69e-03

Pos logit contributions
otion+0.008
 wasting+0.007
 fighting+0.007
 grounded+0.007
 sewing+0.006
Neg logit contributions
 flavor-0.008
boat-0.008
 tal-0.008
imm-0.008
bye-0.008
Token�
Token ID95
Feature activation-6.83e-03

Pos logit contributions
otion+0.018
 wasting+0.017
 fighting+0.017
 grounded+0.016
 sewing+0.016
Neg logit contributions
 flavor-0.015
imm-0.015
bye-0.015
boat-0.015
 tal-0.014
Token€
Token ID26391
Feature activation+1.21e-03

Pos logit contributions
otion+0.013
 wasting+0.012
 fighting+0.011
 grounded+0.011
 sewing+0.011
Neg logit contributions
 flavor-0.011
imm-0.011
boat-0.011
 tal-0.011
bye-0.011
Token�
Token ID129
Feature activation-1.90e-02

Pos logit contributions
 flavor+0.002
boat+0.002
imm+0.002
 tal+0.002
bye+0.002
Neg logit contributions
otion-0.002
 wasting-0.002
 fighting-0.002
 grounded-0.002
 sewing-0.002
Token said
Token ID531
Feature activation+8.36e-03

Pos logit contributions
 flavor+0.006
boat+0.006
imm+0.006
 tal+0.006
bye+0.006
Neg logit contributions
otion-0.005
 wasting-0.004
 fighting-0.004
 grounded-0.004
 sewing-0.004
Token,
Token ID11
Feature activation-1.36e-02

Pos logit contributions
 flavor+0.012
imm+0.012
boat+0.012
 tal+0.012
bye+0.011
Neg logit contributions
otion-0.017
 wasting-0.016
 fighting-0.015
 grounded-0.015
 sewing-0.014
Token "
Token ID366
Feature activation+1.47e-02

Pos logit contributions
otion+0.024
 wasting+0.022
 grounded+0.021
 fighting+0.020
osing+0.019
Neg logit contributions
 flavor-0.023
boat-0.023
 tal-0.022
imm-0.022
bye-0.022
TokenYes
Token ID5297
Feature activation+2.25e-02

Pos logit contributions
 tal+0.031
 flavor+0.030
imm+0.030
iest+0.029
boat+0.029
Neg logit contributions
otion-0.020
 wasting-0.018
 fighting-0.018
 grounded-0.017
Acc-0.017
Token,
Token ID11
Feature activation+1.96e-02

Pos logit contributions
imm+0.038
boat+0.037
 tal+0.037
 flavor+0.036
iest+0.033
Neg logit contributions
otion-0.040
 fighting-0.038
 wasting-0.037
 grounded-0.034
 hey-0.034
Token but
Token ID475
Feature activation+1.30e-02

Pos logit contributions
imm+0.034
 tal+0.033
 flavor+0.032
boat+0.032
iest+0.031
Neg logit contributions
otion-0.034
 wasting-0.033
 fighting-0.032
 grounded-0.031
 sewing-0.029
Token it
Token ID340
Feature activation+6.44e-03

Pos logit contributions
imm+0.022
 tal+0.022
boat+0.022
 flavor+0.021
iest+0.021
Neg logit contributions
otion-0.023
 wasting-0.022
 fighting-0.021
 grounded-0.020
 sewing-0.019
Token hurts
Token ID20406
Feature activation+1.08e-02

Pos logit contributions
 flavor+0.011
boat+0.011
 tal+0.011
imm+0.011
bye+0.011
Neg logit contributions
otion-0.011
 wasting-0.011
 fighting-0.010
 grounded-0.010
 sewing-0.009
Token.
Token ID13
Feature activation+1.32e-02

Pos logit contributions
imm+0.017
 flavor+0.017
 tal+0.017
boat+0.017
iest+0.016
Neg logit contributions
otion-0.020
 wasting-0.019
 fighting-0.018
 grounded-0.018
 sewing-0.017
Token I
Token ID314
Feature activation-1.01e-02

Pos logit contributions
 flavor+0.024
imm+0.024
boat+0.024
 tal+0.023
iest+0.023
Neg logit contributions
otion-0.022
 wasting-0.020
 fighting-0.019
 grounded-0.019
 sewing-0.018
Token should
Token ID815
Feature activation-1.80e-02

Pos logit contributions
otion+0.017
 wasting+0.015
 fighting+0.014
 grounded+0.014
 sewing+0.014
Neg logit contributions
 flavor-0.019
 tal-0.018
boat-0.018
imm-0.018
bye-0.018
Token it
Token ID340
Feature activation+2.54e-02

Pos logit contributions
imm+0.012
boat+0.012
 tal+0.012
 flavor+0.011
bye+0.011
Neg logit contributions
otion-0.013
 wasting-0.012
 fighting-0.011
 grounded-0.011
 sewing-0.011
Token was
Token ID373
Feature activation+1.87e-02

Pos logit contributions
 tal+0.048
boat+0.046
imm+0.044
bye+0.044
oy+0.044
Neg logit contributions
otion-0.041
 fighting-0.039
 wasting-0.039
 grounded-0.036
 sewing-0.033
Token a
Token ID257
Feature activation+2.43e-02

Pos logit contributions
boat+0.034
imm+0.034
bye+0.033
iest+0.033
 flavor+0.033
Neg logit contributions
 wasting-0.030
otion-0.029
 fighting-0.029
 grounded-0.028
 sewing-0.027
Token treasure
Token ID14068
Feature activation+2.57e-02

Pos logit contributions
imm+0.036
boat+0.034
 tal+0.033
 flavor+0.032
bye+0.032
Neg logit contributions
otion-0.047
 wasting-0.047
 fighting-0.046
 grounded-0.045
 sewing-0.044
Token!"
Token ID2474
Feature activation+2.74e-04

Pos logit contributions
imm+0.040
 tal+0.039
 flavor+0.038
boat+0.037
bye+0.036
Neg logit contributions
otion-0.049
 wasting-0.046
 fighting-0.045
 grounded-0.044
 sewing-0.043
Token
Token ID198
Feature activation+5.35e-03

Pos logit contributions
 flavor+0.000
boat+0.000
imm+0.000
 tal+0.000
bye+0.000
Neg logit contributions
otion-0.001
 wasting-0.001
 fighting-0.001
 grounded-0.000
 sewing-0.000
Token
Token ID198
Feature activation-7.71e-03

Pos logit contributions
 flavor+0.008
imm+0.008
boat+0.008
 tal+0.008
iest+0.008
Neg logit contributions
otion-0.010
 wasting-0.010
 fighting-0.009
 grounded-0.009
 sewing-0.009
TokenThe
Token ID464
Feature activation-2.36e-02

Pos logit contributions
otion+0.015
 wasting+0.014
 fighting+0.013
 grounded+0.013
 sewing+0.013
Neg logit contributions
 flavor-0.012
boat-0.012
 tal-0.011
bye-0.011
imm-0.011
Token man
Token ID582
Feature activation-4.01e-02

Pos logit contributions
otion+0.066
osing+0.061
Acc+0.061
 wasting+0.060
 fighting+0.057
Neg logit contributions
 flavor-0.019
boat-0.017
bye-0.016
 carrot-0.016
 rod-0.015
Token picks
Token ID11103
Feature activation-2.93e-02

Pos logit contributions
otion+0.074
 wasting+0.068
Acc+0.068
 sewing+0.065
osing+0.063
Neg logit contributions
 flavor-0.062
 carrot-0.056
 tal-0.055
imm-0.055
 flavour-0.054
Token up
Token ID510
Feature activation-6.77e-03

Pos logit contributions
otion+0.057
 wasting+0.054
osing+0.050
 grounded+0.050
Acc+0.049
Neg logit contributions
 flavor-0.044
boat-0.042
bye-0.040
 tal-0.040
 carrot-0.039
Token little
Token ID1310
Feature activation-3.34e-02

Pos logit contributions
otion+0.115
 wasting+0.103
 grounded+0.100
osing+0.100
oled+0.099
Neg logit contributions
 flavor-0.042
 flavour-0.037
 carrot-0.036
bye-0.035
ww-0.033
Token girl
Token ID2576
Feature activation+1.16e-02

Pos logit contributions
otion+0.076
 wasting+0.069
 grounded+0.069
assing+0.066
osing+0.066
Neg logit contributions
 flavor-0.046
est-0.040
bye-0.040
iest-0.040
 flavour-0.039
Token was
Token ID373
Feature activation-5.01e-03

Pos logit contributions
 flavor+0.018
boat+0.017
imm+0.017
 tal+0.017
bye+0.017
Neg logit contributions
otion-0.022
 wasting-0.021
 fighting-0.020
 grounded-0.020
 sewing-0.019
Token very
Token ID845
Feature activation+1.19e-02

Pos logit contributions
otion+0.010
 wasting+0.009
 fighting+0.009
 grounded+0.008
 sewing+0.008
Neg logit contributions
 flavor-0.008
 tal-0.008
boat-0.008
imm-0.007
bye-0.007
Token scared
Token ID12008
Feature activation-1.24e-02

Pos logit contributions
 flavor+0.023
boat+0.023
imm+0.023
 tal+0.022
bye+0.022
Neg logit contributions
otion-0.018
 wasting-0.018
 fighting-0.017
 grounded-0.016
 sewing-0.015
Token.
Token ID13
Feature activation-1.81e-02

Pos logit contributions
otion+0.026
 wasting+0.025
 grounded+0.024
 fighting+0.023
 sewing+0.023
Neg logit contributions
 flavor-0.016
 tal-0.016
boat-0.015
imm-0.015
iest-0.015
Token She
Token ID1375
Feature activation-1.18e-03

Pos logit contributions
otion+0.027
 wasting+0.025
 grounded+0.023
 fighting+0.023
 sewing+0.021
Neg logit contributions
 tal-0.035
 flavor-0.035
bye-0.035
imm-0.035
boat-0.034
Token had
Token ID550
Feature activation-1.74e-02

Pos logit contributions
otion+0.002
 wasting+0.002
 fighting+0.002
 grounded+0.002
 sewing+0.002
Neg logit contributions
 flavor-0.002
boat-0.002
imm-0.002
 tal-0.002
bye-0.002
Token never
Token ID1239
Feature activation+2.32e-02

Pos logit contributions
otion+0.037
 wasting+0.033
 fighting+0.031
 grounded+0.031
osing+0.030
Neg logit contributions
 flavor-0.025
 tal-0.025
boat-0.023
imm-0.023
bye-0.023
Token climbed
Token ID19952
Feature activation-3.30e-02

Pos logit contributions
imm+0.043
boat+0.042
 flavor+0.041
 tal+0.040
ww+0.040
Neg logit contributions
 wasting-0.037
otion-0.036
 fighting-0.034
 grounded-0.033
 sewing-0.031
Token a
Token ID257
Feature activation+2.22e-02

Pos logit contributions
otion+0.068
 wasting+0.061
 grounded+0.060
 fighting+0.058
osing+0.057
Neg logit contributions
 flavor-0.048
 tal-0.047
boat-0.046
imm-0.045
iest-0.045
Token,
Token ID11
Feature activation-4.10e-02

Pos logit contributions
otion+0.014
 wasting+0.013
 fighting+0.012
 grounded+0.012
 sewing+0.012
Neg logit contributions
 flavor-0.011
imm-0.010
boat-0.010
 tal-0.010
bye-0.010
Token but
Token ID475
Feature activation-2.54e-02

Pos logit contributions
otion+0.089
 wasting+0.080
 grounded+0.079
osing+0.075
 sewing+0.075
Neg logit contributions
 flavor-0.053
boat-0.048
 flavour-0.046
 tal-0.046
bye-0.045
Token she
Token ID673
Feature activation+2.24e-03

Pos logit contributions
otion+0.044
 wasting+0.040
 grounded+0.038
 fighting+0.037
Acc+0.037
Neg logit contributions
 flavor-0.044
boat-0.040
bye-0.039
 flavour-0.039
 tal-0.039
Token wanted
Token ID2227
Feature activation-1.33e-03

Pos logit contributions
 flavor+0.004
boat+0.004
 tal+0.004
imm+0.004
bye+0.004
Neg logit contributions
otion-0.004
 wasting-0.004
 fighting-0.003
 grounded-0.003
 sewing-0.003
Token to
Token ID284
Feature activation+2.87e-02

Pos logit contributions
otion+0.003
 wasting+0.003
 fighting+0.003
 grounded+0.003
 sewing+0.002
Neg logit contributions
 flavor-0.002
boat-0.002
 tal-0.002
imm-0.002
bye-0.002
Token go
Token ID467
Feature activation-5.19e-03

Pos logit contributions
imm+0.059
 tal+0.056
boat+0.056
ww+0.055
iest+0.053
Neg logit contributions
otion-0.041
 wasting-0.040
 fighting-0.039
 sewing-0.036
 grounded-0.036
Token with
Token ID351
Feature activation-1.29e-03

Pos logit contributions
otion+0.009
 wasting+0.009
 fighting+0.008
 grounded+0.008
 sewing+0.008
Neg logit contributions
 flavor-0.009
boat-0.009
 tal-0.008
imm-0.008
bye-0.008
Token her
Token ID607
Feature activation-1.13e-02

Pos logit contributions
otion+0.002
 wasting+0.002
 fighting+0.001
 grounded+0.001
 sewing+0.001
Neg logit contributions
 flavor-0.003
boat-0.003
 tal-0.003
imm-0.003
bye-0.003
Token mom
Token ID1995
Feature activation-1.32e-02

Pos logit contributions
otion+0.022
 wasting+0.021
 grounded+0.019
 fighting+0.019
osing+0.018
Neg logit contributions
 flavor-0.018
 tal-0.017
boat-0.017
imm-0.016
bye-0.016
Token.
Token ID13
Feature activation-1.30e-02

Pos logit contributions
otion+0.026
 wasting+0.024
 grounded+0.022
 fighting+0.022
osing+0.021
Neg logit contributions
 flavor-0.021
boat-0.020
 tal-0.020
imm-0.019
bye-0.019
Token She
Token ID1375
Feature activation-3.20e-04

Pos logit contributions
otion+0.025
 wasting+0.024
 grounded+0.022
 fighting+0.022
 sewing+0.021
Neg logit contributions
 flavor-0.020
 tal-0.019
bye-0.019
imm-0.019
boat-0.019
Token ran
Token ID4966
Feature activation-1.61e-02

Pos logit contributions
otion+0.042
 wasting+0.039
 grounded+0.036
 fighting+0.036
 sewing+0.035
Neg logit contributions
 flavor-0.033
boat-0.032
 tal-0.032
imm-0.032
bye-0.031
Token away
Token ID1497
Feature activation+5.29e-03

Pos logit contributions
otion+0.038
 wasting+0.035
 fighting+0.033
 grounded+0.032
 sewing+0.032
Neg logit contributions
bye-0.018
boat-0.018
 flavor-0.018
 tal-0.017
imm-0.016
Token and
Token ID290
Feature activation+4.78e-05

Pos logit contributions
 flavor+0.008
boat+0.008
imm+0.008
 tal+0.008
bye+0.008
Neg logit contributions
otion-0.010
 wasting-0.009
 fighting-0.009
 grounded-0.009
 sewing-0.008
Token hid
Token ID24519
Feature activation-3.69e-02

Pos logit contributions
 flavor+0.000
boat+0.000
imm+0.000
 tal+0.000
bye+0.000
Neg logit contributions
otion-0.000
 wasting-0.000
 fighting-0.000
 grounded-0.000
 sewing-0.000
Token behind
Token ID2157
Feature activation-2.43e-02

Pos logit contributions
otion+0.068
 wasting+0.061
osing+0.060
 grounded+0.059
Acc+0.058
Neg logit contributions
 flavor-0.056
boat-0.056
 tal-0.054
iest-0.054
bye-0.052
Token a
Token ID257
Feature activation+9.66e-04

Pos logit contributions
otion+0.049
 wasting+0.045
 grounded+0.044
osing+0.043
 fighting+0.042
Neg logit contributions
 flavor-0.037
 tal-0.035
bye-0.033
boat-0.033
 flavour-0.032
Token tree
Token ID5509
Feature activation-1.13e-02

Pos logit contributions
 flavor+0.001
imm+0.001
boat+0.001
 tal+0.001
bye+0.001
Neg logit contributions
otion-0.002
 wasting-0.002
 fighting-0.002
 grounded-0.002
 sewing-0.002
Token.
Token ID13
Feature activation-3.42e-02

Pos logit contributions
otion+0.025
 wasting+0.023
 fighting+0.022
 grounded+0.022
osing+0.021
Neg logit contributions
 flavor-0.014
boat-0.014
 tal-0.014
imm-0.014
bye-0.013
Token She
Token ID1375
Feature activation-1.37e-02

Pos logit contributions
otion+0.052
 wasting+0.050
 grounded+0.050
 fighting+0.047
osing+0.044
Neg logit contributions
bye-0.060
 flavor-0.060
 tal-0.059
 His-0.059
imm-0.055
Token cried
Token ID16896
Feature activation-1.57e-02

Pos logit contributions
otion+0.027
 wasting+0.024
 fighting+0.023
 grounded+0.022
osing+0.022
Neg logit contributions
 flavor-0.022
 tal-0.021
boat-0.021
imm-0.020
bye-0.020
Token and
Token ID290
Feature activation-1.89e-03

Pos logit contributions
otion+0.031
 wasting+0.029
 fighting+0.027
 grounded+0.027
osing+0.026
Neg logit contributions
 flavor-0.023
 tal-0.023
bye-0.023
boat-0.023
imm-0.022
Token They
Token ID1119
Feature activation-1.35e-02

Pos logit contributions
 flavor+0.004
boat+0.004
imm+0.004
 tal+0.004
bye+0.004
Neg logit contributions
otion-0.004
 wasting-0.004
 fighting-0.004
 grounded-0.004
 sewing-0.004
Token saw
Token ID2497
Feature activation-1.12e-02

Pos logit contributions
otion+0.026
 wasting+0.024
 grounded+0.023
 sewing+0.022
 fighting+0.022
Neg logit contributions
 flavor-0.021
boat-0.020
 tal-0.020
imm-0.020
bye-0.020
Token a
Token ID257
Feature activation+2.04e-02

Pos logit contributions
otion+0.021
 wasting+0.020
 grounded+0.019
 fighting+0.019
osing+0.018
Neg logit contributions
 flavor-0.017
boat-0.017
 tal-0.017
imm-0.016
bye-0.016
Token boy
Token ID2933
Feature activation-3.38e-02

Pos logit contributions
imm+0.033
 tal+0.031
boat+0.031
bye+0.030
 flavor+0.030
Neg logit contributions
otion-0.037
 wasting-0.037
 fighting-0.036
 sewing-0.034
 grounded-0.034
Token running
Token ID2491
Feature activation-2.50e-03

Pos logit contributions
otion+0.058
 wasting+0.054
 grounded+0.051
Acc+0.051
osing+0.049
Neg logit contributions
 flavor-0.057
boat-0.055
oy-0.053
 tal-0.052
oc-0.052
Token towards
Token ID3371
Feature activation-2.83e-02

Pos logit contributions
otion+0.005
 wasting+0.005
 fighting+0.005
 grounded+0.004
 sewing+0.004
Neg logit contributions
 flavor-0.004
boat-0.004
 tal-0.004
imm-0.004
bye-0.003
Token them
Token ID606
Feature activation-1.76e-02

Pos logit contributions
otion+0.055
 wasting+0.051
 grounded+0.049
osing+0.048
Acc+0.047
Neg logit contributions
 flavor-0.045
 tal-0.041
bye-0.041
boat-0.041
 flavour-0.038
Token.
Token ID13
Feature activation+7.68e-03

Pos logit contributions
otion+0.040
 wasting+0.038
 grounded+0.037
Acc+0.035
 sewing+0.035
Neg logit contributions
 flavor-0.020
boat-0.019
 tal-0.019
imm-0.018
bye-0.018
Token The
Token ID383
Feature activation-4.82e-03

Pos logit contributions
 flavor+0.011
imm+0.011
boat+0.011
 tal+0.010
iest+0.010
Neg logit contributions
otion-0.016
 wasting-0.015
 fighting-0.015
 grounded-0.014
 sewing-0.014
Token boy
Token ID2933
Feature activation+1.92e-02

Pos logit contributions
otion+0.009
 wasting+0.009
 fighting+0.008
 grounded+0.008
 sewing+0.008
Neg logit contributions
 flavor-0.007
boat-0.007
 tal-0.007
bye-0.007
imm-0.007
Token was
Token ID373
Feature activation+1.96e-03

Pos logit contributions
boat+0.031
imm+0.031
iest+0.031
 tal+0.031
bye+0.031
Neg logit contributions
otion-0.034
 fighting-0.033
 wasting-0.033
 grounded-0.030
 sewing-0.029
Token He
Token ID679
Feature activation+1.32e-02

Pos logit contributions
boat+0.013
 flavor+0.013
imm+0.013
iest+0.013
 tal+0.012
Neg logit contributions
otion-0.028
 wasting-0.026
 fighting-0.026
 grounded-0.025
 sewing-0.025
Token heard
Token ID2982
Feature activation+1.14e-02

Pos logit contributions
 flavor+0.024
imm+0.023
boat+0.023
 tal+0.023
iest+0.023
Neg logit contributions
otion-0.021
 wasting-0.020
 fighting-0.020
 grounded-0.019
 sewing-0.018
Token his
Token ID465
Feature activation+2.07e-02

Pos logit contributions
imm+0.019
 flavor+0.019
boat+0.019
 tal+0.018
bye+0.018
Neg logit contributions
otion-0.021
 wasting-0.019
 fighting-0.019
 grounded-0.018
 sewing-0.017
Token mom
Token ID1995
Feature activation-2.94e-02

Pos logit contributions
imm+0.041
boat+0.041
 flavor+0.040
iest+0.039
ww+0.039
Neg logit contributions
otion-0.030
 fighting-0.030
 wasting-0.029
 grounded-0.027
 crying-0.027
Token and
Token ID290
Feature activation+1.60e-02

Pos logit contributions
otion+0.044
 wasting+0.041
 grounded+0.039
Acc+0.038
osing+0.037
Neg logit contributions
 flavor-0.054
imm-0.053
boat-0.053
 tal-0.052
oy-0.051
Token dad
Token ID9955
Feature activation-4.23e-02

Pos logit contributions
imm+0.028
 flavor+0.028
bye+0.027
 tal+0.026
boat+0.026
Neg logit contributions
otion-0.028
 wasting-0.027
 fighting-0.026
 grounded-0.025
 sewing-0.024
Token talking
Token ID3375
Feature activation-1.93e-02

Pos logit contributions
otion+0.073
Acc+0.069
 wasting+0.069
 grounded+0.067
osing+0.065
Neg logit contributions
 flavor-0.064
boat-0.063
oy-0.062
imm-0.059
 tal-0.059
Token to
Token ID284
Feature activation-3.82e-03

Pos logit contributions
otion+0.042
 wasting+0.041
 grounded+0.039
 fighting+0.037
osing+0.037
Neg logit contributions
 flavor-0.024
boat-0.023
imm-0.022
bye-0.022
iest-0.022
Token someone
Token ID2130
Feature activation-2.68e-02

Pos logit contributions
otion+0.006
 wasting+0.006
 fighting+0.006
 grounded+0.006
 sewing+0.005
Neg logit contributions
 flavor-0.007
boat-0.007
 tal-0.007
imm-0.007
bye-0.006
Token.
Token ID13
Feature activation+5.63e-03

Pos logit contributions
otion+0.060
 wasting+0.057
 grounded+0.055
Acc+0.054
osing+0.053
Neg logit contributions
 flavor-0.031
boat-0.029
imm-0.028
iest-0.027
 tal-0.026
Token He
Token ID679
Feature activation+1.20e-02

Pos logit contributions
 flavor+0.008
boat+0.008
imm+0.008
 tal+0.008
iest+0.008
Neg logit contributions
otion-0.012
 wasting-0.011
 fighting-0.011
 grounded-0.010
 sewing-0.010
Token They
Token ID1119
Feature activation-2.26e-02

Pos logit contributions
boat+0.030
iest+0.030
 flavor+0.029
imm+0.029
 tal+0.028
Neg logit contributions
otion-0.023
 wasting-0.021
 fighting-0.021
 grounded-0.019
 sewing-0.019
Token do
Token ID466
Feature activation-1.62e-02

Pos logit contributions
otion+0.048
 wasting+0.044
 fighting+0.041
 sewing+0.041
 grounded+0.041
Neg logit contributions
boat-0.031
 flavor-0.031
 tal-0.030
bye-0.029
imm-0.028
Token not
Token ID407
Feature activation+2.17e-02

Pos logit contributions
otion+0.028
 wasting+0.025
 grounded+0.024
 fighting+0.024
 sewing+0.023
Neg logit contributions
 flavor-0.028
boat-0.027
imm-0.027
 tal-0.026
bye-0.026
Token see
Token ID766
Feature activation+3.60e-04

Pos logit contributions
imm+0.047
 flavor+0.045
 tal+0.045
boat+0.044
ww+0.044
Neg logit contributions
otion-0.029
 wasting-0.028
 fighting-0.028
 grounded-0.025
 hey-0.023
Token Fl
Token ID1610
Feature activation-1.50e-02

Pos logit contributions
 flavor+0.001
boat+0.001
imm+0.001
 tal+0.001
bye+0.001
Neg logit contributions
otion-0.001
 wasting-0.001
 fighting-0.001
 grounded-0.001
 sewing-0.001
Tokenuffy
Token ID15352
Feature activation-5.12e-02

Pos logit contributions
otion+0.025
 wasting+0.025
 grounded+0.023
 fighting+0.022
Acc+0.021
Neg logit contributions
imm-0.026
 flavor-0.026
boat-0.025
 tal-0.025
bye-0.024
Token watching
Token ID4964
Feature activation-2.34e-02

Pos logit contributions
otion+0.097
Acc+0.092
 grounded+0.091
 wasting+0.089
Girls+0.085
Neg logit contributions
 flavor-0.072
boat-0.070
 carrot-0.067
imm-0.064
iest-0.063
Token them
Token ID606
Feature activation+2.44e-03

Pos logit contributions
otion+0.034
 wasting+0.032
 grounded+0.031
osing+0.029
 fighting+0.029
Neg logit contributions
 flavor-0.045
 tal-0.043
boat-0.043
imm-0.043
bye-0.042
Token from
Token ID422
Feature activation-3.53e-02

Pos logit contributions
 flavor+0.004
imm+0.004
 tal+0.004
boat+0.004
bye+0.004
Neg logit contributions
otion-0.005
 wasting-0.004
 fighting-0.004
 grounded-0.004
 sewing-0.004
Token the
Token ID262
Feature activation-4.24e-03

Pos logit contributions
otion+0.073
osing+0.067
 grounded+0.064
 wasting+0.063
Acc+0.063
Neg logit contributions
 flavor-0.049
 tal-0.047
 carrot-0.044
boat-0.044
 bait-0.043
Token shore
Token ID15191
Feature activation+3.88e-03

Pos logit contributions
otion+0.010
 wasting+0.010
 fighting+0.009
 grounded+0.009
osing+0.009
Neg logit contributions
 flavor-0.005
boat-0.004
 tal-0.004
imm-0.004
bye-0.004
Token moment
Token ID2589
Feature activation-1.27e-02

Pos logit contributions
imm+0.014
 tal+0.014
boat+0.014
 flavor+0.014
bye+0.013
Neg logit contributions
otion-0.023
 wasting-0.022
 fighting-0.021
 grounded-0.021
 sewing-0.021
Token.
Token ID13
Feature activation-3.30e-02

Pos logit contributions
otion+0.027
 wasting+0.025
 grounded+0.024
 fighting+0.024
osing+0.023
Neg logit contributions
 flavor-0.017
boat-0.016
 tal-0.016
bye-0.016
imm-0.016
Token She
Token ID1375
Feature activation+1.44e-02

Pos logit contributions
otion+0.053
 wasting+0.050
 grounded+0.048
 fighting+0.044
osing+0.042
Neg logit contributions
bye-0.058
 flavor-0.058
 His-0.057
 tal-0.056
imm-0.055
Token felt
Token ID2936
Feature activation-2.01e-02

Pos logit contributions
boat+0.026
 tal+0.025
iest+0.025
 flavor+0.025
imm+0.025
Neg logit contributions
otion-0.023
 wasting-0.022
 fighting-0.022
 grounded-0.021
 sewing-0.020
Token sorry
Token ID7926
Feature activation-2.01e-02

Pos logit contributions
otion+0.036
 wasting+0.033
 fighting+0.032
 grounded+0.030
 sewing+0.030
Neg logit contributions
 flavor-0.033
 tal-0.032
boat-0.031
bye-0.031
imm-0.030
Token for
Token ID329
Feature activation-5.75e-02

Pos logit contributions
otion+0.040
 wasting+0.039
 grounded+0.035
 fighting+0.035
osing+0.034
Neg logit contributions
 flavor-0.028
bye-0.026
 tal-0.026
boat-0.026
imm-0.026
Token Max
Token ID5436
Feature activation-3.42e-02

Pos logit contributions
otion+0.102
 grounded+0.101
osing+0.094
pler+0.090
Acc+0.088
Neg logit contributions
 flavor-0.082
 his-0.077
 he-0.074
 trick-0.073
 carrot-0.072
Token too
Token ID1165
Feature activation-1.06e-02

Pos logit contributions
otion+0.081
 wasting+0.075
 grounded+0.072
osing+0.070
Acc+0.069
Neg logit contributions
 flavor-0.038
boat-0.034
 tal-0.034
bye-0.033
 carrot-0.031
Token.
Token ID13
Feature activation-2.86e-02

Pos logit contributions
otion+0.023
 wasting+0.022
 grounded+0.021
 fighting+0.021
 sewing+0.021
Neg logit contributions
 flavor-0.013
 tal-0.012
bye-0.012
boat-0.012
imm-0.012
Token She
Token ID1375
Feature activation+3.86e-03

Pos logit contributions
otion+0.046
 wasting+0.043
 grounded+0.040
 fighting+0.037
osing+0.036
Neg logit contributions
bye-0.052
 flavor-0.052
 His-0.051
 tal-0.050
imm-0.049
Token said
Token ID531
Feature activation-1.15e-02

Pos logit contributions
 flavor+0.006
boat+0.006
imm+0.006
 tal+0.006
iest+0.006
Neg logit contributions
otion-0.007
 wasting-0.007
 fighting-0.007
 grounded-0.007
 sewing-0.006
Token was
Token ID373
Feature activation-2.49e-02

Pos logit contributions
otion+0.082
 wasting+0.080
 grounded+0.077
 fighting+0.074
Acc+0.074
Neg logit contributions
 flavor-0.041
boat-0.037
iest-0.035
imm-0.035
 flavour-0.034
Token always
Token ID1464
Feature activation-2.54e-03

Pos logit contributions
otion+0.049
 wasting+0.043
 grounded+0.042
 fighting+0.041
osing+0.041
Neg logit contributions
 flavor-0.039
 tal-0.036
boat-0.035
imm-0.035
 flavour-0.035
Token more
Token ID517
Feature activation-1.58e-02

Pos logit contributions
otion+0.005
 wasting+0.004
 fighting+0.004
 grounded+0.004
 sewing+0.004
Neg logit contributions
 flavor-0.004
boat-0.004
imm-0.004
 tal-0.004
bye-0.004
Token.
Token ID13
Feature activation-3.52e-02

Pos logit contributions
otion+0.034
 wasting+0.031
 fighting+0.029
 grounded+0.029
osing+0.028
Neg logit contributions
 flavor-0.022
 tal-0.021
imm-0.021
iest-0.020
boat-0.020
Token
Token ID198
Feature activation-1.80e-02

Pos logit contributions
otion+0.080
 wasting+0.078
 fighting+0.072
 grounded+0.072
assing+0.068
Neg logit contributions
 tal-0.039
 flavor-0.038
 His-0.038
imm-0.036
bye-0.035
Token
Token ID198
Feature activation-5.81e-02

Pos logit contributions
otion+0.041
 wasting+0.040
 fighting+0.038
 grounded+0.037
 sewing+0.035
Neg logit contributions
 flavor-0.021
 tal-0.020
imm-0.020
boat-0.019
bye-0.019
TokenL
Token ID43
Feature activation-5.90e-02

Pos logit contributions
otion+0.146
 wasting+0.137
 fighting+0.134
 weeping+0.125
 arguing+0.122
Neg logit contributions
ww-0.057
His-0.054
bye-0.048
 flavor-0.046
boat-0.044
Tokenily
Token ID813
Feature activation-3.15e-02

Pos logit contributions
 fighting+0.091
 wasting+0.090
assing+0.089
 typing+0.085
Fighting+0.080
Neg logit contributions
iest-0.104
imm-0.103
est-0.097
 flavor-0.096
ade-0.092
Token started
Token ID2067
Feature activation-4.51e-02

Pos logit contributions
otion+0.075
 wasting+0.068
 fighting+0.062
 grounded+0.061
osing+0.061
Neg logit contributions
 flavor-0.037
 tal-0.036
bye-0.035
imm-0.035
boat-0.035
Token to
Token ID284
Feature activation-4.20e-02

Pos logit contributions
otion+0.124
 grounded+0.111
osing+0.109
 wasting+0.108
 hey+0.105
Neg logit contributions
 flavor-0.034
 tal-0.033
 flavour-0.027
 trick-0.024
 place-0.023
Token feel
Token ID1254
Feature activation-4.22e-02

Pos logit contributions
otion+0.084
 grounded+0.073
osing+0.072
 wasting+0.071
ains+0.066
Neg logit contributions
 flavor-0.065
 tal-0.059
 flavour-0.058
bye-0.054
 dive-0.054
Token.
Token ID13
Feature activation+2.56e-04

Pos logit contributions
 flavor+0.001
boat+0.001
imm+0.001
 tal+0.001
bye+0.000
Neg logit contributions
otion-0.001
 wasting-0.001
 fighting-0.001
 grounded-0.001
 sewing-0.001
Token
Token ID198
Feature activation-7.18e-04

Pos logit contributions
 flavor+0.000
boat+0.000
imm+0.000
 tal+0.000
bye+0.000
Neg logit contributions
otion-0.000
 wasting-0.000
 fighting-0.000
 grounded-0.000
 sewing-0.000
Token
Token ID198
Feature activation-1.83e-02

Pos logit contributions
otion+0.001
 wasting+0.001
 fighting+0.001
 grounded+0.001
 sewing+0.001
Neg logit contributions
 flavor-0.001
boat-0.001
imm-0.001
 tal-0.001
bye-0.001
TokenTim
Token ID14967
Feature activation-2.25e-02

Pos logit contributions
otion+0.040
 wasting+0.037
 fighting+0.036
 grounded+0.035
 sewing+0.034
Neg logit contributions
 flavor-0.024
boat-0.023
ww-0.023
bye-0.023
imm-0.022
Token saw
Token ID2497
Feature activation-7.52e-03

Pos logit contributions
otion+0.050
 wasting+0.046
 fighting+0.043
 grounded+0.042
osing+0.041
Neg logit contributions
 flavor-0.029
imm-0.028
bye-0.028
 tal-0.028
boat-0.028
Token Lily
Token ID20037
Feature activation-5.80e-02

Pos logit contributions
otion+0.015
 wasting+0.014
 grounded+0.013
 fighting+0.013
osing+0.012
Neg logit contributions
 flavor-0.011
 tal-0.011
boat-0.011
imm-0.011
bye-0.010
Token with
Token ID351
Feature activation-4.78e-03

Pos logit contributions
otion+0.106
Girls+0.101
 grounded+0.099
Acc+0.097
 hey+0.096
Neg logit contributions
 flavor-0.087
 carrot-0.076
 flavour-0.075
 sound-0.075
 nut-0.073
Token his
Token ID465
Feature activation+2.77e-03

Pos logit contributions
otion+0.009
 wasting+0.009
 fighting+0.008
 grounded+0.008
osing+0.008
Neg logit contributions
 flavor-0.007
 tal-0.007
boat-0.007
imm-0.007
bye-0.007
Token aer
Token ID9551
Feature activation+8.72e-03

Pos logit contributions
 flavor+0.004
imm+0.004
boat+0.004
 tal+0.004
bye+0.004
Neg logit contributions
otion-0.006
 wasting-0.005
 fighting-0.005
 grounded-0.005
 sewing-0.005
Tokenopl
Token ID20106
Feature activation-2.23e-02

Pos logit contributions
 flavor+0.014
boat+0.013
imm+0.013
 tal+0.013
bye+0.012
Neg logit contributions
otion-0.017
 wasting-0.015
 fighting-0.015
 grounded-0.015
 sewing-0.014
Tokenane
Token ID1531
Feature activation-8.25e-03

Pos logit contributions
 wasting+0.043
otion+0.043
 fighting+0.040
 grounded+0.040
 sewing+0.038
Neg logit contributions
boat-0.033
imm-0.032
 flavor-0.032
bye-0.031
iest-0.031
Token shines
Token ID32481
Feature activation+1.87e-03

Pos logit contributions
otion+0.026
 wasting+0.024
 fighting+0.022
 grounded+0.022
osing+0.021
Neg logit contributions
 flavor-0.024
boat-0.023
imm-0.023
 tal-0.023
bye-0.022
Token again
Token ID757
Feature activation+2.83e-02

Pos logit contributions
 flavor+0.003
boat+0.003
 tal+0.003
imm+0.003
bye+0.003
Neg logit contributions
otion-0.003
 wasting-0.003
 fighting-0.003
 grounded-0.003
 sewing-0.002
Token.
Token ID13
Feature activation+8.82e-03

Pos logit contributions
imm+0.057
boat+0.056
 tal+0.055
 flavor+0.054
iest+0.054
Neg logit contributions
 wasting-0.038
 fighting-0.037
otion-0.037
 sewing-0.034
 grounded-0.033
Token
Token ID198
Feature activation-4.53e-03

Pos logit contributions
boat+0.016
imm+0.015
 flavor+0.015
 tal+0.015
iest+0.015
Neg logit contributions
otion-0.015
 wasting-0.014
 fighting-0.014
 grounded-0.013
 sewing-0.013
Token
Token ID198
Feature activation-1.74e-02

Pos logit contributions
otion+0.009
 wasting+0.009
 fighting+0.008
 grounded+0.008
 sewing+0.008
Neg logit contributions
 flavor-0.006
boat-0.006
 tal-0.006
imm-0.006
bye-0.006
TokenThey
Token ID2990
Feature activation-6.04e-02

Pos logit contributions
otion+0.036
 wasting+0.033
 fighting+0.031
 grounded+0.030
 sewing+0.029
Neg logit contributions
 flavor-0.025
boat-0.025
ww-0.025
bye-0.024
 tal-0.023
Token take
Token ID1011
Feature activation+1.59e-02

Pos logit contributions
otion+0.136
 wasting+0.120
Acc+0.117
 fighting+0.116
Fighting+0.116
Neg logit contributions
 flavor-0.072
boat-0.070
 dive-0.069
 carrot-0.067
bye-0.066
Token turns
Token ID4962
Feature activation-2.95e-02

Pos logit contributions
imm+0.031
boat+0.031
 flavor+0.030
 tal+0.029
iest+0.029
Neg logit contributions
otion-0.023
 wasting-0.022
 fighting-0.022
 grounded-0.021
 sewing-0.020
Token holding
Token ID4769
Feature activation-1.29e-02

Pos logit contributions
otion+0.058
 grounded+0.053
 wasting+0.052
Acc+0.050
osing+0.050
Neg logit contributions
 flavor-0.042
boat-0.038
 tal-0.038
 flavour-0.037
imm-0.037
Token the
Token ID262
Feature activation-3.24e-02

Pos logit contributions
otion+0.025
 wasting+0.023
 grounded+0.022
 fighting+0.022
osing+0.021
Neg logit contributions
 flavor-0.020
 tal-0.019
boat-0.019
imm-0.019
 flavour-0.018
Token button
Token ID4936
Feature activation+7.36e-03

Pos logit contributions
otion+0.073
 wasting+0.066
osing+0.065
 grounded+0.063
Acc+0.061
Neg logit contributions
 flavor-0.047
boat-0.042
 carrot-0.041
iest-0.040
 tal-0.040